Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
cs.RO
Submitted: 2025-12-10
Updated: 2026-09-18
Comments: 94 pages, 10 figures, npj Robotics Version 3
Code: https://github.com/Genesis-Embodied-AI/Genesis
License: http://creativecommons.org/licenses/by/4.0/
The gist: Contact-rich tasks pose significant challenges for robotic systems due to inherent uncertainty, complex dynamics, and the high risk of damage during interaction.
Terminology
Abstract
Contact-rich tasks pose significant challenges for robotic systems due to inherent uncertainty, complex dynamics, and the high risk of damage during interaction. Recent advances in learning-based control have shown great potential in enabling robots to acquire and generalize complex manipulation skills in such environments, but ensuring safety, both during exploration and execution, remains a critical bottleneck for reliable real-world deployment. This survey provides a comprehensive overview of safe learning-based methods for robot contact-rich tasks. We categorize existing approaches into two main domains: safe exploration and safe execution. We review key techniques, including constrained reinforcement learning, risk-sensitive optimization, uncertainty-aware modeling, control barrier functions, and model predictive safety shields, and highlight how these methods incorporate prior knowledge, task structure, and online adaptation to balance safety and efficiency. A particular emphasis of this survey is on how these safe learning principles extend to and interact with emerging robotic foundation models, especially vision-language models (VLMs) and vision-language-action models (VLAs), which unify perception, language, and control for contact-rich manipulation. We discuss both the new safety opportunities enabled by VLM/VLA-based methods, such as language-level specification of constraints and multimodal grounding of safety signals, and the amplified risks and evaluation challenges they introduce. Finally, we outline current limitations and promising future directions toward deploying reliable, safety-aligned, and foundation-model-enabled robots in complex contact-rich environments. More details and materials are available at our Project GitHub Repository.
Sources
- Towards Safe Robot Foundation Models
- CompliantVLA-adaptor: VLM-Guided Variable Impedance Action for Safe Contact-Rich Manipulation
- Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey
- Compare Contact Model-based Control and Contact Model-free Learning: A Survey of Robotic Peg-in-hole Assembly Strategies
- A Survey on Imitation Learning for Contact-Rich Tasks in Robotics
- A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
- Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey
- Towards Forceful Robotic Foundation Models: a Literature Survey
- SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
- Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interaction
- ManiFeel: Benchmarking and Understanding Visuotactile Manipulation Policy Learning
- Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning
- Multimodal Diffusion Forcing for Forceful Manipulation
- Safe and Optimal Variable Impedance Control via Certified Reinforcement Learning
- Learning to be Safe: Deep RL with a Safety Critic
- STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models
- PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability
- Audio-VLA: Adding Contact Audio Perception to Vision-Language-Action Model for Robotic Manipulation
- End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies