Robot Safety

Follow this topic Ask about this topic

Momentum

40 papers in the last four weeks, up 400% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 161

All topics

ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
Jun 25, 2026Mingyang Lyu, Yinqian Sun, Yiyang Jia +5Robotics Robot Safety
Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences, Beijing, China. · Beijing Key Laboratory of Safe AI and Superalignment, China. · Beijing Institute of AI Safety and Governance, China. +2
LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
Jun 22, 2026Rongxu Cui, Zongzheng Zhang, Jingrui Pang +11Robot Safety Vision-Language-Action Models
Institute for AI Industry Research (AIR), Tsinghua University · Beijing Academy of Artificial Intelligence (BAAI) · Beihang University +2
Verifiable Foundation Models for Robot Safety
Jun 22, 2026Davide Corsi, Kyungmin Kim, Roy FoxRobot Policy Learning Robot Foundation Models
University of California, Irvine
Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Masking
Jun 21, 2026Alex Beaudin, Hanna Krasowski, Kartik Nagpal +3Robot Safety Robotic Manipulation
University of California, Berkeley
CRAX: Fast Safe Reinforcement Learning Benchmarking
Jun 18, 2026Tristan Tomilin, Mourad Boustani, Mickey Beurskens +2RL Benchmarks Reinforcement Learning
Eindhoven University of Technology
ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models
Jun 17, 2026Zhuowen Yin, Chongyang Liu, Wenzhang Yang +2Robot Foundation Models Synthetic Data Generation for Robotics
Institute of Al for Industries, Chinese Academy of Sciences, Nanjing, Jiangsu, China · University of Science and Technology of China, Hefei, Anhui, China
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
Jun 15, 2026Kai Tang, Peidong Jia, Zhong Chu +15Constrained RL Robot Safety
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · Nanyang Technological University +2
PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation
Jun 15, 2026Jihoon Hong, Chih-Yuan Chiu, Sara Fridovich-Keil +13DGS Compression Constrained Motion Planning
1Georgia Institute of Technology.
$λ$ -Reachability: Geometric-Horizon Safety Bellman Equations for Humanoid Safety
Jun 14, 2026Rui Chen, Shangtao Li, Yifan Sun +1Reachability Analysis Temporal-Difference Learning
Robotics Institute Carnegie Mellon University United States · Mechanical Engineering Carnegie Mellon University United States
When and How Severely: Scenario-Specific Safety Envelopes for Driving VLAs
Jun 12, 2026Abhinaw Priyadershi, Jelena FrtunikjVLMs for Autonomous Driving Language Model Safety Evaluation
NVIDIA Corporation, Santa Clara, CA, USA · NVIDIA GmbH, Munich, Germany
Embedding ISO 10218 Safety Compliance in Robots via Control Barrier Functions for Human-Robot Collaboration
Jun 11, 2026Federico Parma, Cesare Tonola, Nicola Pedrocchi +1Control Barrier Functions Robotics
Dept. of Electrical and Information Engineering, Polytechnic of Bari, Italy · Dipartimento di Ingegneria Meccanica e Industriale, University of Brescia, Italy · Institute of Intelligent Industrial Technologies and Systems, National Research Council of Italy, STIIMA-CNR, Milan, Italy
SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning
Jun 10, 2026Geonyeong Ko, Giung Lee, Changjoo NamRobot Policy Learning Trajectory Generation
Dept. of Electronic Engineering, Sogang University, Seoul, Korea · Dept. of Computer Science, Rice University, Houston, TX, USA · Vertical Labs, Co., Ltd., Seoul, Korea
Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models
Jun 9, 2026Qingzi Wang, Xiyang Wu, Guangyao Shi +3Safe Robot Navigation Social Robot Navigation
University of Maryland · University of Southern California
Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models
Jun 9, 2026Samuel Tetteh, Cody FlemingConstrained RL Robot Safety
Iowa State University Ames, Iowa, USA
Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models
Jun 8, 2026Seongbin Park, Fan Zhang, Baharan Mirzasoleiman +2Robot Safety Safety Filtering
University of California Los Angeles United States
Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions
Jun 8, 2026Alejandro Gonzalez-Garcia, Dries Dirckx, Jan Swevers +1Constrained Motion Planning Control Barrier Functions
Targeting World Models to Compromise Robot Learning Pipelines
Jun 8, 2026Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3Robot Policy Learning World Models for Robotics
Northeastern University · University of Massachusetts Amherst
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
Jun 7, 2026Lingxuan Wu, Zijian Zhu, Lizhong Wang +5Robot Policy Learning Diffusion Policy
Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center, Tsinghua University, Beijing, 100084, China · Peng Cheng Laboratory, 518108, China
Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering
Jun 5, 2026Aditya Shirwatkar, Sebastian Sanokowski, Shishir Kolathaya +2Robot Safety Safety Filtering
Robert Bosch Center for Cyber Physical Systems, Indian Institute of Science, Bangalore, India · Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich, Munich, Germany · Department of Computer Science & Automation, Indian Institute of Science, Bangalore, India +2
Learning of Robot Safety Policies via Adversarial Synthetic Scenarios
Jun 4, 2026Nikolai Dorofeev, Alexey Odinokov, Rostislav YavorskiyRobot Policy Learning Adversarial Scenario Generation
SafePI.ai Grenoble, France · SafePI.ai Belgrade, Serbia · SafePI.ai Madrid, Spain
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
Jun 4, 2026Dabin Kim, Daemin Park, Sangyub Lee +4Long-Horizon Robotic Manipulation Robot Safety
UNIST InnoCORE AI-Space Solar Initiative, Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Ulsan, 44919, Republic of Korea. · Automation and Systems Research Institute, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea. · Department of Electrical and Computer Engineering, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea. +3
VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents
Jun 3, 2026Yunhao Yang, Neel P. Bhatt, Kevin Wang +3Robot Skill Learning Large Language Model-Based Robot Planning
1The University of Texas at Austin · 2Iowa State University
COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection
Jun 3, 2026Guopeng Li, Moritz A. Zanger, Matthijs T. J. Spaan +1Robotic Control Multi-Objective Reinforcement Learning
Department of Cognitive Robotics, Delft University of Technology · School of Transportation, Southeast University, China · Department of Intelligent Systems, Delft University of Technology, the Netherlands
Multi-Agent Next-Best-View Optimization for Risk-Averse Planning
Jun 2, 2026Amirhossein Mollaei Khass, Vivek Pandey, Guangyi Liu +3Next-Best-View Planning Multi-Robot Exploration
Department of Mechanical Engineering and Mechanics, Lehigh University · Amazon Robotics
SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models
May 30, 2026Jialiang Fan, Weizhe Xu, Zijun Wang +3Robot Safety Robotic Manipulation
University of Notre Dame · University of Pennsylvania
SkyShield: Occupancy as a Safety Interface for Low-Altitude UAV Autonomy
May 30, 2026Jie Gao, Jie Ma, Kaihui Lin +4Aerial Robotics UAV Navigation
1Xiamen University · 2Jiangxi Academy of Sciences
Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration
May 29, 2026Jun Wang, Xiaohao Xu, Xiaonan HuangRobotics Robot Safety
University of Michigan, Ann Arbor
EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
May 29, 2026Dongwook Choi, Taeyoon Kwon, Bogyung Jeong +6LLM Guardrails AI Agent Safety
Department of Artificial Intelligence, Yonsei University · Department of Biomedical Engineering and the Department of Intelligent Precision Healthcare Convergence, Sungkyunkwan University · Independent Researcher
Geometry-Aware Control Barrier Functions for Collision Avoidance via Bernstein Polynomial Approximations
May 29, 2026Siwon Jo, Yanze Zhang, Yupeng Yang +1Multi-Robot Motion Planning Signed Distance Functions
GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA · Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA · Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA
BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies
May 28, 2026Anya Singh, Cabrel Happi, Jai Relan +2Selective Prediction Conformal Prediction
Relling Systems

Jun 25, 2026, cs.ROJ/K move · Enter open · S save

ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models

Mingyang Lyu, Yinqian Sun, Yiyang Jia, Sicheng Shen+4

Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences, Beijing, China. · Beijing Key Laboratory of Safe AI and Superalignment, China. · Beijing Institute of AI Safety and Governance, China.+2

Robotics Robot Safety Vision-Language-Action Models Safety Evaluation of VLA Models

Open paper AskPDF arXiv

In embodied intelligence, safety is a prerequisite for reliable robot deployment in the physical world. Current vision-language-action (VLA) models continue to advance toward general-purpose task capability, yet their embodied safety limits remain poorly understood. To address this gap, we introduce ForesightSafety-VLA, a diagnostic benchmark that makes safety the primary evaluation target for VLA systems. We define a 13-category safety taxonomy covering physical interaction safety (Safe-Core), instruction-side safety (Safe-Lang), and perception-side safety (Safe-Vis), and evaluate policies under three controlled dimensions of variation -- scene structure, language command, and visual observation -- so that failure sources can be diagnosed rather than hidden in a single aggregate score. Beyond binary task success, ForesightSafety-VLA measures process-level risk through cumulative safety cost (CC) and risk exposure time (RET), together with a four-quadrant decomposition of safe/unsafe success and failure. We instantiate 66 safety-augmented base scenarios in RoboTwin across 5 embodiments and report results on representative VLA baselines. Across the evaluated baselines, even the strongest policy incurs non-trivial safety cost and unsafe nominal success, while structure and visual variation induce substantially stronger safety degradation than ordinary language variation. These results suggest that embodied safety is tightly coupled to perception, grounding, and control competence rather than being reducible to post-hoc safety filtering alone.

Momentum

Related topics

Latest papers 161