機械人

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Amazon SVP wrote 100,000 lines of code with AI after 25-year break 4 min read Key takeaways Amazon’s AI tools are designed for everyone, whether or not one has a technical background. Amazon’s HR leader used AI to write…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Maria Sukhareva Aug 25, 2026 ∙ Paid Hype-free executive briefing on last week’s critical AI developments, complete with ready-to-present slides for your team. If you are a paid subscriber, you can listen to the radar in…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Research · Original data · Post-application snapshot The State of AI Disclosure 2026 1088 detector-flagged EU-facing sites scannedScanned Monday 10 August 2026Rule pack 2026.07.9 Eight days after Article 50 of the EU AI…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Nvidia Corp. today announced the release of Jetson Orin Nano 2, a robotics computer “brain” for running artificial intelligence and frontier-level models at the edge. In the past months, foundational AI models have grown smaller and more efficient, adding numerous capabilities alongside language understanding, computer vision and audio processing. As more AI models compress in […] The post Nvidia doubles compute for entry-level edge robotics with Jetson Orin Nano 2 appeared first on SiliconANGLE.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The Chinese automaker’s robotics arm will use the funds to accelerate rollout of its humanoid Iron.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Singapore-based robotics data infrastructure firm Ropedia Pte. Ltd. today announced the launch of HOMIE Gen2, the next generation of the company’s head-mounted wearable that records human movement data to train robots. Smart robotics requires tremendous amounts of high-quality data taken from various environments. Most of the training data used to build the artificial intelligence foundation […] The post Ropedia launches next-gen wearable capture device for robotic AI training data appeared first on SiliconANGLE.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.21410v1 Announce Type: new Abstract: Robots are increasingly entering everyday environments where privacy is shaped not only by data practices, but also by spatial, bodily, social, and relational boundaries. Their embodied capabilities allow them to reshape these boundaries through situated action, challenging privacy framings centered on data flows, interface settings, or one-time consent. Prior work has examined robot privacy through sensing, data collection, telepresence, transparency, consent, bystander awareness, and multi-stakeholder governance. Building on this work, we propose embodied boundary privacy as a capability-by-context framing for examining how physically present robots may reshape privacy boundaries in situated interaction. Specifically, this framing organizes privacy risks across seven robot capabilities and five deployment contexts, asking how embodied capabilities enable boundary crossings and how situated contexts shape who is affected, how these crossings are interpreted, and when they become contested. We use this perspective to outline design and research implications for embodied privacy mechanisms, including boundary checkpoints, viewpoint-aware sensing control, remote-presence disclosure, object- and body-level access rules, constraints on socially persuasive privacy influence, and local interruption rights. We encourage HRI research, design, and governance to treat robot movement, orientation, proximity, object access, remote presence, and social expression as privacy-relevant actions whose meaning depends on context.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.21404v1 Announce Type: new Abstract: Fixed coordinate measuring machines (CMMs) and portable articulated-arm CMMs are often assigned to the same inspection task, but their nominal accuracy specifications do not show whether a change of instrument will preserve the disposition of a part. The question is not simply how far the two results differ, but whether that difference crosses the tolerance boundary. We examined this issue with recorded measurements of cylindrical, cubic, and spherical features under nominal 20 {\deg}C and 30 {\deg}C conditions. Repeated records and two roughness profiles without sufficient acquisition information were removed, leaving six dimensional and four form profiles. For each dimensional feature, the distances of the two system means from nominal define the exact tolerance interval in which the systems receive opposite direct labels. The fixed-CMM stream was approximately 11.2 {\mu}m higher than the articulated-arm stream at both conditions. All four form profiles fell on opposite sides of the recorded 10 {\mu}m upper limit. The dimensional disagreement intervals also overlapped strongly; their mean widths were 6.573 {\mu}m at 20 {\deg}C and 4.995 {\mu}m at 30 {\deg}C. The results clarify why an average difference between instruments is not, by itself, a measure of substitution risk. The proposed tolerance map identifies the feature-tolerance combinations for which instrument choice can change the recorded inspection label and, therefore, where a controlled equivalence study and a task-specific uncertainty budget are needed before substitution.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.21390v1 Announce Type: new Abstract: Inertial navigation systems are specialized navigation apparatuses that equip almost all autonomous underwater and surface vehicles. They require precise initial alignment, i.e., determination of their initial attitude, which is typically achieved: (a) in quasi-static conditions (whenever possible); and (b) in two stages: Coarse Alignment (CA), using methods like TRI-axis Attitude Determination (TRIAD), and Fine Alignment (FA), via Zero Velocity Update (ZVU)-based Extended Kalman Filtering (EKF). However, conventional methods suffer from slow convergence and limited bias estimability. In response, this paper introduces: (a) an optimized version of a recently proposed CA method, namely, TRIAD with Coarse Bias Estimation (TRIAD-CBE); and (b) a novel FA EKF observation model that incorporates Non-Orthonormality (NON) error constraints derived from TRIAD, directly linking these errors to the inertial sensor biases. As validated through extensive Monte Carlo (MC) simulations, as well as real-world experiments using two Inertial Measurement Units (IMUs) of different grades, our approaches substantially accelerate the convergence of misalignment and bias estimates (from minutes to seconds), while maintaining accuracy/precision comparable to traditional techniques.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.21388v1 Announce Type: new Abstract: Reliable and continuous human tracking is essential for natural human-robot interaction, particularly for companion robots. However, many existing approaches rely on wearable tags or fixed cameras with limited fields of view, which reduces system flexibility and often causes tracking failures when the target moves outside the sensing range. In this paper, we present a human tracking approach based on a gimbal-mounted camera integrated into a mobile robot. By actively controlling the gimbal mechanism, the camera can dynamically adjust its viewing direction to maintain the target within the field of view, even under substantial relative motion between the robot and the human. Furthermore, a continual learning strategy is applied to the person re-identification (ReID) task to adapt to changes in appearance and environmental conditions during long-term tracking. Experimental results demonstrate that the proposed system significantly improves the stability and continuity of human tracking, enables real-time re-identification, and provides responsive feedback for reliable tracking of human motion from walking to running. User studies further indicate that the proposed approach enhances user comfort by eliminating the need for wearable tags.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.21426v1 Announce Type: new Abstract: The garment manufacturing industry is under increasing pressure to improve product quality, reduce costs, and accelerate digital transformation toward Industry 4.0. One of the most challenging quality-control activities is sewing-line inspection, where defects such as broken stitches and skipped stitches are difficult to detect consistently through manual inspection. Human-based inspection is often affected by fatigue, subjective judgement, and inconsistent performance, resulting in defect leakage, rework, and reduced production efficiency. This study presents the development and validation of an Artificial Intelligence (AI)-based visual inspection system for garment sewing-line quality control. The system utilizes Convolutional Neural Networks (CNNs) to detect sewing defects and was initially trained using black fabric and black sewing thread samples. Experimental testing was conducted on black, red, dark green, light blue, silver, and fluorescent yellow fabrics. The results demonstrated successful detection of jump sewing-line defects on black, red, and dark green materials, while performance limitations were observed for broken sewing-line defects and fabrics with significantly different visual characteristics, including light blue, silver, and fluorescent yellow colours. These findings indicate that model accuracy is strongly influenced by the diversity of training data and the ability to generalize across different fabric and thread colours.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Generalist AI has released GEN-1.5, a robot foundation model that learns a new physical task from a single demonstration. Drop 3–12 seconds of sensorimotor data into its 30-second context window, and the robot performs the task. No gradient updates, no fine-tuning, no task-specific programming. Across 10 diverse manipulation tasks, this one-shot in-context prompting averaged 59% […] The post Generalist AI Releases GEN-1.5: A Robot Foundation Model That Learns New Tasks From One 3–12 Second Demo appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.20891v1 Announce Type: new Abstract: We present a vision-only state estimation system for X-configuration quadcopters equipped with a canonical stereo camera pair and no inertial sensors. The system operates entirely in the body frame, requiring only synchronised stereo images and motor thrust commands. A continuous-discrete extended Kalman filter on a composite manifold state $\langle SE(3), \mathbb{R}^3, \ldots \rangle$ maintains estimates of body-frame pose, velocity, angular velocity, gravity, and disturbances, using stationary scene points as implicit inertial references. Feature points are detected (FAST, Shi-Tomasi), tracked temporally (SSD, Lucas-Kanade) and matched across cameras (NCC), with search regions predicted from filter-derived pose and point uncertainty. Chi-squared gating on the normalised innovation admits only stationary points to the filter. The system also produces a sparse 3D point cloud carrying per-point position, velocity and joint covariance. These come from a 4-view (two stereo pairs at two timestamps) full bundle adjustment that jointly estimates position and velocity from stereo disparity and temporal parallax, with the filter-derived relative pose as a prior. Feature points in the EKF do not enter the solver; their information is reflected through the pose prior. Point cloud density is spatially adaptive: an external focus point directs allocation, producing dense coverage in the region of attention and sparse coverage elsewhere. The output is a body-frame state estimate, a calibrated pose change, and a sparse scene flow. It is intended as a measurement source for a downstream world model anchored in the current body frame, without dependence on GPS, IMU, or any world-frame infrastructure, though the architecture accommodates their future integration.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.20823v1 Announce Type: new Abstract: A humanoid has infinitely many ways to stand up from sitting while maintaining balance, making sit-to-stand (STS) a challenging control problem. We synthesise natural humanoid STS motion from scratch using reinforcement learning, without demonstrations or reference trajectories. A single Proximal Policy Optimisation policy learns smooth, human-like rising driven by three complementary components. (i) A coupled force/chair-height curriculum is used. A vertical pelvis-assist force aids early trajectory exploration and decays over training. Taller chairs are unlocked with decaying assisting force. This ensures that the policy masters a viable STS trajectory at each chair height before being exposed to harder ones, avoiding the premature distribution shift that otherwise collapses generalisation. (ii) Motion robustness is achieved by randomly sampling from a large number of inverse kinematics-generated initial and target poses spanning over eight chair heights. (iii) A set of rewards is defined inspired from biomechanics and optimal control studies. They shape the robot's angular momentum for seat-off, and enable support-region transition via centre of pressure attraction function to ensure smooth low-effort actuation. On a deterministic force-free evaluator, the policy attains more than 97% balanced-standing success across eight chair heights. The policy generalises smooth motion across chair heights and enables the robot to rise from substantially deep-seated postures as compared to the state of the art.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.20784v1 Announce Type: new Abstract: Imitation learning for robotics depends on human demonstrations, some of which people may later ask to remove. Retraining without them is the natural reference, but its cost grows with policy and dataset scale, motivating cheaper operators that edit a trained policy. Metrics inherited from machine unlearning, such as forgetting loss or a single membership attack, do not establish what an edit removed from a policy acting in closed loop. We therefore introduce a retrain-calibrated audit that reads demonstration unlearning along two axes: behavior, whether the edited policy acts like one retrained without the removed demonstrations, and evidence, whether an auditor can still detect it was trained on them. The behavior axis measures action divergence to that retrain at matched states, calibrated by a floor built from independent retrains, so a policy at the floor is as close to a retrain as retrains are to each other. The evidence axis applies a per-demonstration membership attack against a retrain null, reporting both its rank and its absolute member-loss level, since rank alone accepts operators that inflate member losses past the null. A conformal test then combines both axes into one hypothesis of joint retrain consistency, against a fleet of independent retrains large enough to reject at conventional significance. Across five preregistered conditions on three real-robot policy classes and two simulation suites, the axes dissociate in both directions on one checkpoint, as an edit may repair task behavior while leaving evidence unchanged, or reduce evidence while moving behavior away from retraining. On the ACT arm, a redirect edit restores blind-scored robot success to 18 of 20 trials.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.20655v1 Announce Type: new Abstract: Planning and control of fixed-wing Unmanned Aerial Vehicles (UAVs) are challenging due to nonlinear dynamics, aerodynamic limits, and environmental disturbances. Differential flatness offers a principled way to generate fast, feasible trajectories, but its use has largely been confined to model-free controllers, which lack predictive capabilities and demand tuning. In this paper, we propose a unified framework that integrates differential flatness-based trajectory generation with Nonlinear Model Predictive Control (NMPC), combining computationally efficient planning with predictive, constraint-aware control. To further improve robustness, we introduce a wind-aware sampling strategy embedded within the NMPC framework, enabling the generation of dynamically feasible reference trajectories that proactively account for wind disturbances while strictly enforcing aerodynamic and control input constraints. We validate the proposed framework through extensive simulations and real-world flight experiments, demonstrating improved tracking accuracy and robustness for complex trajectories, particularly when using the proposed wind-aware sampling strategy under strong wind conditions.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.20433v1 Announce Type: new Abstract: Advances in technology have led to increasingly sophisticated musical humanoid robots. However, their use has largely been limited to performance and related research in human-robot interaction. In this position paper, we propose a novel perspective: musical humanoid robots as experimental interfaces for investigating music-evoked emotions. We argue that current research is constrained by paradigms relying on pre-recorded auditory stimuli, which fail to capture the multimodal, embodied, and interactive nature of real-world musical experience. Building on existing theories of music cognition and emotion, we identify mechanisms that require controlled manipulation of both acoustic and non-acoustic variables. We show that humanoid robots are well-suited as they enable parametric control of performance variables, reproducibility across trials, and the decoupling and recombination of auditory, visual, and interactive components. We illustrate the technical feasibility of this perspective through a case study of the WAseda Saxophonist Robot 5 (WAS-5), demonstrating reproducible control of acoustic and interaction variables that are prerequisites for future music-emotion experiments. Our work positions musical humanoid robots as a methodological platform that enables future controlled investigations of music-evoked emotions.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI and Chauffeur Knowledge In Poor Charlie’s Almanac, Charlie Munger tells a story that really struck me. “Max Planck, after he won the Nobel Prize, went around Germany giving the same standard lecture on the new quantu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Embedded AI | No Starch Press Skip to main content WANT SWEET DEALS? JOIN OUR MAILING LIST Embedded AI Intelligence at the Deep Edge Available September 2026, 600 pp. ISBN-13: 9781718504905 Download Chapter 9: Sensor Ma…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI frontend skill pack Change what your agent reaches for. Registry-routed. Machine-enforced. Anti-slop by default — a request loads exactly one of 19 skills, and everything it writes is held to 60 checks before it ship…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：It’s clear here in Silicon Valley that AI is advancing faster than humans’ ability to control it. That means even sober prophecies seem optimistic Here in Silicon Valley, the experts think that within the next couple of years we’ll see an extraordinary takeoff for artificial intelligence. “Welcome to the foothills of the singularity,” as a Stanford University friend greeted me. More prosaically, the imminent breakthrough is described as “recursive self-improvement” – the point at which AI itself trains each successive model of AI, resulting in an exponential development to something which, in many significant respects, is more intelligent than us humans. As Robert Wright puts it in his book The God Test: “Never before has the near-term future … held such a wide array of not-implausible paths for humankind that would be so wildly transformative.” But will this be heaven or hell? Heaven, says Elon Musk, who predicts “an age of amazing abundance” – although he also sees a 10-20% chance of killer robots murdering us all. Hell is more likely according to Geoffrey Hinton, one of the intellectual founding fathers of AI. “My intuition is, we’re toast,” he told an interviewer in 2023. And talking to Sebastian Mallaby, author of The Infinity Machine, a book about the quest for superintelligence, Hinton estimates p(doom) – the probability of human extinction – at 50%, “because I haven’t got a clue how to estimate the real number”. “As soon as evolution [of AI] kicks in, we’re fucked,” he adds cheerfully. But whether it’s God or Godzilla, artificial superintelligence is just around the corner. Timothy Garton Ash is a Guardian columnist Continue reading...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Post Log inSign up Post Ole Lehmann on X: "i think AI is about to uncover an entire hidden world of animal communication and what it's already found is insane... > AI found evidence that elephants call each other by nam…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Over the past few days, a number of prominent filmmaking content creators including Matti Haapoja and Sam "Kold" Kolder have posted videos of themselves demonstrating what's possible with AI platform Higgsfield. The videos highlight Higgsfield's recently added Seedance 2.5 functionality and pitch these technologies as the future of video production. In response to these videos, other creators started sharing what appear to be screenshots of partnership offers they'd received from PR firms working on Higgsfield's behalf. All of this led fans to the conclusion that Higgsfield has been trying to use creators to boost its profile and garner goo … Read the full story at The Verge.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：When the biotech company Insilico Medicine used its computer models to propose a promising drug for pulmonary fibrosis, it enthusiastically claimed in a press release that the molecule had been “discovered by” its gener…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.19522v1 Announce Type: new Abstract: Scan-to-map LiDAR odometry drifts unboundedly along the unobservable axes of geometrically degenerate environments like tunnels and corridors, and existing degeneracy handling requires environment-specific parameter tuning. This paper presents a parameter-free approach. We show that in voxelized GICP the Gauss--Newton (GN) Hessian masks translational degeneracy, because covariance regularization keeps the translation block artificially well-conditioned. We bypass this with a regularization-free voxel-normal localizability field and two of its statistics: a normalized fraction $f_0$ detecting directional anisotropy, and an absolute per-voxel mass $\lambda_0$ distinguishing information absence (tunnels) from dilution (dense open scenes). A temporal-median gate combines both to trigger Fisher-information correspondence weighting. Calibrated once by fixed rules on two short sequences and then frozen, LF-GICP achieves the lowest KITTI relative translation error ($0.865\%$) under an identical evaluation protocol against re-run baselines, outperforms them on GEODE tunnels and MulRan, leads the HeLiPR mean, and generalizes across four sensor types without re-tuning. We further demonstrate empirically that straight, uniform tunnels remain unobservable along their axis for LiDAR-only registration.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.19490v1 Announce Type: new Abstract: State-of-the-art vision-language-action (VLA) models such as $\pi_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining can cause severe performance drops. Finetuning the VLA on in-domain expert data from the new embodiment improves performance on the expert task but leads to a loss in its original instruction following and behavioral priors. In this paper, we propose a self-supervised method that generates online interaction rollouts from the zero-shot VLA as additional training data for finetuning. Our experiments show this finetuning scheme yields strong multi-task policies that, on the target robot, (1) inherit prior tasks distilled from the zero-shot model, (2) enable generalist instruction following, while (3) learning new skills from expert data with improved sample efficiency. We demonstrate the success of our approach across test sets probing generalization on a real ALOHA robot and a new simulation benchmark in RoboTwin. Video results are available at https://self-supervised-control.pages.dev/

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.19453v1 Announce Type: new Abstract: Stream-based robotics Task and Motion Planning (TAMP) integrates discrete symbolic planning with dynamically generated continuous geometric parameters, such as poses, grasps, and trajectories. However, stream-based planners typically reason only about goal reachability, whereas long-horizon tasks also demand adherence to temporal specifications, such as safety-critical ordering, invariance, and liveness constraints. No methods currently exist to enforce such temporal constraints for stream-based solvers because streams generate an expanding geometric object set via iterative stream refinement loops during planning, rendering existing temporal-logic compilation techniques incompatible. We therefore present Synchronous Action Monitoring with Token Destruction (SAM-TD), a compilation method that enforces arbitrary Linear Temporal Logic over finite traces ($\textrm{LTL}_f$) specifications in stream-based TAMP. SAM-TD translates arbitrary $\textrm{LTL}_f$ constraints into automata and embeds regressed automaton guards into action schemas, which are pre-specified before planning begins. By doing so, SAM-TD can handle objects generated by streams during planning, thus circumventing the need to enumerate a fixed object set or modify the underlying planner. During search, SAM-TD synchronously updates automaton states and uses a validity token shared across all automata to prune constraint-violating branches. We show that SAM-TD supports dynamically generated stream objects from iterative stream refinements during plan search. Experimental results provide the first ever demonstration of stream-based TAMP under $\textrm{LTL}_f$ constraints in three robotics PDDLStream environments. Furthermore, on standard discrete PDDL benchmarks, SAM-TD is competitive with state-of-the-art temporal-constraint compilation methods.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.19372v1 Announce Type: new Abstract: A fundamental challenge in robotic teleoperation is enabling an operator to control a remote robot as effortlessly and intuitively as their own hands. Despite the growing use of teleoperation to collect demonstration data for training autonomous robot policies, teleoperated robot performance still falls significantly short of human dexterity, even for basic tasks. Here, we present evidence that a key factor contributing to this performance gap is the absence of spatially distributed tactile feedback. Using a two-degree-of-freedom (DoF) bilateral force-feedback telemanipulator paired with a 32-DoF tactile fingertip display, we show that operator performance improves significantly when localized deformations on the remote manipulator are faithfully reproduced on the operator's fingertip. In a series of teleoperation tasks, reproducing distributed contact information not only accelerated task performance but also brought teleoperated movements closer to natural human behavior by minimizing corrective actions and task completion steps, thereby reducing the deviation between teleoperated and natural trajectories by 29$\unicode{x2013}$79%. Furthermore, we found that increasing the resolution of the tactile feedback$\unicode{x2014}$by refining how finely the measured displacements were quantized for reproduction$\unicode{x2014}$compressed the state-space distribution of teleoperated motions, which has been associated with improved training outcomes for autonomous robot policies. Together, these results suggest that spatially distributed tactile feedback is essential for closing the gap between human and teleoperated dexterity and training the next generation of autonomous robots.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.19281v1 Announce Type: new Abstract: Programming robots remains challenging for non-experts, as traditional methods require expert knowledge and even block-based interfaces often lack flexibility. Recent work has explored Large Language Models (LLMs) to automatically generate robot programs from natural language, but these systems remain limited by a lack of transparency, missing mechanisms to ensure alignment with user intent, and little support for reuse. We present APPROVE (AI-Powered Programming for Robots with Visual End-User Feedback), an LLM-based multi-modal end-user programming framework that integrates natural language input with a block-based interface and an explicit user confirmation step. Generated programs are visualized using a block-based interface in Blockly, allowing users to confirm, modify, or reject them before execution. Confirmed functions are stored in a library for reuse, gradually building a set of reliable program components. Our approach contributes a human-centered design for LLM-based robot programming that emphasizes user trust, intent alignment, and reusability.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.19536v1 Announce Type: new Abstract: Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics. We propose CVSD-Reg, a robust global LiDAR registration framework that distills visual semantic priors from a vision foundation model into LiDAR representations. In Stage 1, a Point Transformer V3 student learns from a frozen DINOv2 teacher through contrastive distillation and spherical-manifold alignment, which preserves the hyperspherical geometry of the teacher embedding space. Self-supervised InfoNCE consistency and soft $\mathrm{SE}(3)$ invariance further encourage viewpoint-robust descriptors. In Stage 2, the distilled representation is adapted to registration through correspondence learning, density-aware point-dropout augmentation, and end-to-end pose optimization. With a single checkpoint, CVSD-Reg generalizes to both single-sensor and zero-shot cross-sensor scenarios without sensor-specific adaptation and remains entirely camera-free at inference. On KITTI, nuScenes, and HeLiPR, CVSD-Reg achieves strict success rate ([email protected]\,m/$1^\circ$) of 97.7$\%$, 99.0$\%$, and 99.3$\%$, respectively, including 97.3$\%$ on sparse 16-beam Velodyne scans. It outperforms state-of-the-art geometric registration methods by up to 44.0 percentage points without requiring camera inputs or post-hoc ICP refinement.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Taylor Belrose Aug 19, 2026 Summary: AI can never develop consciousness, sentience, or moral status, no matter how intelligent it becomes, and no matter how convincingly it simulates human behavior. This is because AIs…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The Q7 M5+ is a strong value robot vacuum for households that want reliable mapping and an auto-empty dock without flagship pricing.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18433v1 Announce Type: new Abstract: Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, and broader benchmarks should improve generalization. In robotics, however, a model can generalize while work still remains before it can run on a robot with a particular body. The work required differs across methods and target robots, and those differences affect practical deployment. We call the gap between reusable models, representations, or data and their use in execution on the target robot the embodiment gap. This survey examines what can be reused across robot embodiments and what must still be implemented on a new robot. We place existing methods on a two-axis map that shows the type of shared structure and the stage at which adaptation is needed for execution on the target robot. We then examine recent work through three overlapping research directions: sharing semantics and perception, sharing robot data and interfaces, and learning correspondence across embodiments. We also propose a reporting framework for adaptation work that success rate alone does not reveal. The framework identifies the work that should be checked when comparing cross-embodiment learning and highlights work that remains on a new robot and questions for future study.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18364v1 Announce Type: new Abstract: Pneumatic artificial muscles have provided new opportunities to develop upper-extremity soft exosuits for reha- bilitation, augmentation, and assisted daily living. However, the complex dynamics and limited bandwidth of these actuators has made providing responsive assistance based on user intention a longstanding challenge. In this work, we present an inverse-plant control strategy for pneumatically actuated soft exosuits that only relies on kinematic sensing for task-agnostic and dynamic assistance during daily living. We model the human-robot system using a Hammerstein dynamic model, consisting of a Preisach hysteresis model and a linear time-invariant filter, to capture the static and dynamic behavior of the system. We personalize our model to each user using 140 s of data and approximate an inverse to integrate into our control loop. When evaluated on a test rig that emulated a soft assistive exosuit for the wrist, our controller reduced the interaction torque by up to 73% and the activation of key flexor and extensor muscles by up to 47% relative to the condition with no assistance for speeds ranging from 8{\deg}/s to 120{\deg}/s. Overall, this work presents a control strategy that can provide task-agnostic, dynamic assistance with pneumatically actuated soft exosuits without the need for physiological or force sensors to interpret user intention.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18292v1 Announce Type: new Abstract: Consider a robot guide dog escorting a blind user to an available seat while a second assistive robot dog concurrently retrieves a cup of coffee and delivers it to the same seat. This setting motivates concurrent execution because navigation and object retrieval can overlap. A syntactically valid Large Language Model (LLM) plan may still violate embodiment constraints, and successful-looking controller motion does not by itself establish task completion. We introduce \textsc{GuideFetch}, a coordination framework for concurrent navigation and object retrieval by a heterogeneous guider and fetcher team. An LLM instantiates a schedule-conditioned four-action schema from a natural-language instruction. Before execution, robot, skill, and target aliases are normalized, and proposed actions are validated against registered targets, robot capabilities, and the selected schedule. Robot and object states then govern sequential and parallel execution. In a matched $2\times2$ study across 90 combinations of scene and seed (360 executions), all 180 online LLM responses validate without fallback or replay and match the corresponding scripted plans. For each planner source, sequential and parallel execution achieve $72/90$ and $71/90$ operational successes, respectively. Among the 56 cases completed by both schedules, parallel execution reduces mean makespan by 41.3\%. Within this controlled setting, role specialization and action overlap shorten completed missions, while state checks distinguish plan validity from verified mission completion. Source code will be available.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18270v1 Announce Type: new Abstract: Reliable tool--tissue contact detection can support interaction-aware control and downstream force estimation in robot-assisted surgery. Most existing methods learn a contact classifier from RGB appearance, which is hard to generalize. In this work, we use the depth image generated from a stereo pair to give more information about tool--tissue contact. For each depth frame, we localize a spatially supported minimum-distance patch around the tool boundary and reduce it to a single scalar, $-\log_{10}|d|$; this signal rises and falls in step with ground-truth contact. We formalize this observation with a fully supervised two-state hidden Markov model. We fit this model as a six-fold leave-one-session-out (LOSO) ensemble on six palpation sessions against a single silicone cup-like phantom, with the decision threshold selected from the pooled out-of-fold predictions. It is evaluated on four held-out sessions of three categories: 1. same task on same phantom; 2. same task on different phantom; 3. different task on different phantom. This model reaches held-out macro F1 $0.927$ and AUPRC $0.980$. We further compare against a reproduction of an RGB-based contact classifier from prior work. This RGB-based model achieves high performance on the first category (F1 $0.965$), but substantially lower performance on the other two, resulting in macro F1 $0.320$ across all four sessions. These results indicate that the tool--tissue distance is a strong, transferable cue for contact detection in robot-assisted surgery.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18258v1 Announce Type: new Abstract: Robot-Assisted Feeding (RAF) systems are essential for assisting individuals with disabilities or motor impairments in eating tasks. Manipulating granular food items, such as rice and beans, poses significant challenges due to their dynamic physical properties. Learning from human demonstrations offers a promising solution, but acquiring high-quality demonstrations is complex. To address this, we present VERAGMIL, a framework that combines a high-fidelity simulator with an intuitive Virtual Reality (VR) interface for recording demonstrations and supporting different imitation learning methods. VERAGMIL provides a realistic environment for training RAF systems to handle granular materials, including robots, sensors, and various food items with distinct physical characteristics. We evaluate VERAGMIL by training three imitation learning models, BC, BC-RNN, and BCQ, on granular scooping and transporting tasks using both VR interface and 3D space mouse demonstrations, comparing them with a human-expert baseline. The models are assessed on success rate, spillage, generalization to unseen food items, and task completion time. Results show that VR-based demonstrations significantly outperform 3D space mouse data, with BCQ achieving the best overall performance, particularly in reducing spillage and approaching human performance. These findings underscore the effectiveness of our framework for training RAF systems in granular material handling. The code for our framework is publicly available at: https://github.com/AmanuelErgogo/VERAGMIL.git.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18178v1 Announce Type: new Abstract: Trust assessment is a fundamental component of cooperative and connected vehicle systems. However, existing approaches operate primarily at the level of individual vehicles, making it difficult to reason about trust evolution across road segments. In this paper, we propose a spatio-temporal trust-field framework that aggregates microscopic vehicle-level trust into a continuous representation over space and time. The trust field is formally defined on road segments. We conducted simulation-based experiments using synthetic trajectories generated under controlled conditions, enabling analysis of trust-field behavior in simple road scenarios. Beyond theoretical modeling, we study an implication of the trust-field concept: reconstructing the full trust field from sparse roadside-unit (RSU) measurements. We compare (i) a coordinate-based deep learning baseline that learns a generic trust field from sparse samples and (ii) a field-informed deep learning method that treats trust as a latent quantity carried by vehicles and enforces measurement consistency through the aggregation mechanism. The field-informed approach more accurately recovers trajectory-aligned low-trust patterns and yields improved reconstruction error.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18140v1 Announce Type: new Abstract: We define an intertwined scheduling and routing problem where new jobs appear due to the degradation of the existing jobs. Specifically, once a job arrives at a potential job location, a time window begins during which the demand of the job can be fulfilled. The demand degrades within the time window, and once it surpasses a particular threshold, it triggers the arrival of new jobs. Each job location inherently possesses an initial default reward, and the presence of an unprocessed job at a location gradually reduces this default value. The overall objective is to maximize the total remaining reward. The underlying motivation of this problem aligns with the proverb ``a stitch in time saves nine," and the problem itself carries practical implications. We focus on the problem in the context of aerial forest firefighting. Each ignited area has a designated action window; delaying intervention causes the fire to grow, diminishing the area's value and causing it to spread to adjacent areas. We develop a mixed-integer programming model that maximizes value retention in wildfire-threatened regions, and a hybrid model based on dynamic constraint generation to enhance the scalability of the model. We evaluate the performance and practicality of our models through computational experiments and a case study. Additionally, we ensure the study's reproducibility and encourage further research by providing open access to the codebase of our model.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.18240v1 Announce Type: new Abstract: Despite the rapid industrialization of the touch sensor manufacturing process, most of these sensors are still handmade in research laboratories. This complicates standardizing their performance, requiring the repetition of data collection and training models for each unit produced. To address this problem, this paper presents a method that can generalize the estimation of 3D force maps across different GelSight Mini sensor units, regardless of the sensor version. Specifically, the method consists of two stages: a domain adaptation stage, in which the input tactile image is reconstructed as a general tactile image using a UniT-based model; and a stage for estimating 3D force maps employing a U-Net network. Our proposal achieves promising results in both steps, such as an SSIM of 0.9338 +- 0.0358 in the image reconstruction phase and an MAE_F of 1.1294 +- 1.5934(N) in the force estimation phase.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Guide Updated 06/08/2026 Welcome to CIYA! CIYA is a deterministic storage & logic engie for LLMs, it serves as the front brain to an LLM, allowing the benefits of LLMs to shine through, while also preventing as many as…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Self-driving taxi service is advancing around the world.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：We've tested over 50 top robot vacuum-and-mop combos from brands like Roborock, Eufy, Ecovacs, and Dreame to choose the best to keep a home clean.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Why a good API can be invisible to AI agents Imagine this scenario. You've built an excellent API. It's fast, stable, well documented, with clean authentication and a sane architecture. A human developer opens your docs…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The company is the world’s biggest humanoid robot maker by sales.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：1 Join the conversation Follow us Add us as a preferred source on Google A firm that is using AI to locate ancient shipwrecks is sending out a call to seafarers to salvage sunken treasure. The general impression of the…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.17324v1 Announce Type: new Abstract: The continuously deformable geometry of modular robots makes it difficult to define a fixed representation for reconfiguration planning and analysis. This letter introduces a square-cell abstraction that maps deformable rhombus modules to fixed-size grid cells while retaining physically interpretable local motions through two primitives, pivoting and shearing. Under this abstraction, we prove that every non-straight edge-connected configuration with $N \geq 7$ can be transformed to a fixed canonical staircase using only admissible primitive motions. Since these motions are reversible, any two configurations in this class are mutually reconfigurable. The proof is constructive and directly yields a staircase-canonicalization planner that transports removable boundary modules while preserving connectivity. As a practical enhancement, we further introduce a boundary-to-delivery lookahead selector that ranks admissible high level choices without affecting the completeness guarantee. Experiments demonstrate the constructive reconfiguration process and show that the selector substantially reduces planning time, while reference comparisons indicate lower planning times than the prior framework over the shared module counts.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.17320v1 Announce Type: new Abstract: Brachiation is a form of locomotion in which primates move primarily using their arms, enabling traversal in environments without footholds. However, this motion requires highly coordinated whole-body movement and precise timing control for bar grasping and release. As a result, achieving robust behavior on life-sized robotic platforms remains challenging. In this study, we present a reinforcement learning-based method to realize brachiation on a life-sized dual-arm robot. The core of the proposed approach is Waypoint-Guided Reinforcement Learning (WGRL), a learning framework for inducing non-linear and complex motions. For high-difficulty tasks where imitation learning data are unavailable, WGRL guides behavior acquisition by sparsely specifying waypoints for the end-effector trajectory, while whole-body motion is generated through reinforcement learning. In addition, by integrating the waypoint-following guidance with rewards based on task success and mechanical energy, and training in an environment designed for Sim-to-Real transfer, the proposed method achieves both forward progression and motion stability. The acquired behavior is evaluated through Sim-to-Sim experiments under monkey-bar environments with geometric variations and hardware experiments, confirming robust brachiation including failure recovery behavior. This study provides effective learning design guidelines for realizing arm-based locomotion on life-sized robotic hardware and expanding the traversable workspace of robots.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.17146v1 Announce Type: new Abstract: Symbolic planning with PDDL offers a principled framework for long-horizon robot manipulation, but constructing accurate PDDL domain and problem descriptions remains a significant bottleneck, typically requiring substantial domain expertise. We present a Vision-Language Model (VLM)-based approach called PDDL-ART, a framework that autonomously generates task-specific PDDL domain and problem descriptions from a single expert demonstration, a natural language task description, and a library of available high-level action names. PDDL-ART does not require any domain templates, action signatures, or fine-tuning. To ensure the generated descriptions are not only syntactically valid but semantically aligned with the demonstrated task, PDDL-ART introduces a multi-stage correction pipeline operating at syntactic, semantic, and execution levels. A key component of execution-guided correction is symbolic predicate grounding. Instead of relying solely on visual observations, PDDL-ART leverages the tool-use capabilities of modern VLMs to incorporate geometric and temporal reasoning for evaluating relational predicates that are not directly discernible from images alone. Critically, the model autonomously determines when to invoke these tools and how to interpret their outputs. We evaluate PDDL-ART on challenging manipulation tasks in engine maintenance and household domains, including tasks that require memory, abstract predicate inference, and goal states that are visually indistinguishable from the initial state. PDDL-ART achieves an average success rate of 93.3%, compared to 78.3% for a baseline VLM-based planner.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.17027v1 Announce Type: new Abstract: Visual loco-manipulation policies that can generalize to novel scenes and objects have long been a goal of robotics research. However, today's data-hungry algorithms make collecting sufficient demonstrations a struggle for tabletop manipulation, and even more so for humanoids that must also walk and balance. Learning from simulated data and transferring that behavior to the real world, as is commonly done in locomotion, sidesteps this struggle, so we replicate that recipe for loco-manipulation. In doing so, we find that cloning synthetic demonstrations results in a low performance ceiling no matter the amount of training data. Reinforcement learning breaks through it, and refining the cloned policy with Flow-GRPO on a single sparse reward yields performance that synthetic behavior cloning cannot match. Together, these stages form our end-to-end sim-to-real pipeline spanning more than 150,000 scenes, which we use to train FetchMan. We evaluate it on FetchMan-Bench, a simulation benchmark we release, and deploy it zero-shot on a real Unitree G1, where our single-object reach-and-pick policy walks to and grasps a target across unseen scenes at 73.3% success. Finally, we extend this recipe to multi-object training, a first step toward loco-manipulation generalist policies at this data scale.