AI News HubLIVE
Original source2 min read

Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation

Researchers propose a safe reinforcement learning framework for robot navigation that uses Conditional Value-at-Risk (CVaR) constraints during training and neural network reachability verification post-training to ensure safety margins. The method achieves a 98.3% success rate in simulations and successfully transfers to a real robot.

SourcearXiv RoboticsAuthor: Qisong He, Xinmiao Huang, Jinwei Hu, Zhuoyun Li, Yi Dong, Changshun Wu, Xiaowei Huang

[2605.14174] Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation

[Submitted on 13 May 2026]

Title:Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation

View a PDF of the paper titled Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation, by Qisong He and 6 other authors

View PDF HTML (experimental)

Abstract:Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforcement learning (RL) methods assess safety through average cumulative cost. Such metrics can mask dangerous tail-risk behaviors. To address this, we propose a framework that trains risk-sensitive policies through Conditional Value-at-Risk (CVaR) constrained optimization on an off-policy TD3 backbone and evaluates their safety margins post-training through neural network reachability verification. During training, the policy is optimized under CVaR constraints on cumulative costs, promoting sensitivity to high-cost tail outcomes rather than average behavior alone. After training, we compute action reachable sets under bounded observation uncertainty using Taylor Model analysis, yielding a safety rate metric that quantifies the proportion of evaluated states at which the policy's reachable action set remains within prescribed safety margins. A key finding is that policies trained with CVaR constraints maintain larger safety margins from obstacles across evaluated states. This makes them significantly more amenable to formal reachability verification. Experiments across ten navigation scenarios and six baselines show that our method achieves a 98.3\% success rate, the highest safety verification rate among all compared methods, while revealing that average cost rankings and reachability-based safety rankings can diverge. This indicates that reachability verification captures risks which are missed by empirical cost metrics alone. We further validate our approach on a physical Clearpath Jackal robot, demonstrating successful sim-to-real transfer.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2605.14174 [cs.RO]

(or arXiv:2605.14174v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2605.14174

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qisong He [view email] [v1] Wed, 13 May 2026 22:53:47 UTC (4,961 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation, by Qisong He and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)