SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Collision avoidance is key for mobile robots and agents to operate safely in the real world. In this work we present SAFER, an efficient and effective collision avoidance system that is able to improve safety by correcting the control commands sent by an operator. It combines real-world reinforcement learning (RL), search-based online trajectory planning, and automatic emergency intervention, e.g. automatic emergency braking (AEB). The goal of the RL is to learn an effective corrective control action that is used in a focused search for collision-free trajectories, and to reduce the frequency of triggering automatic emergency braking. This novel setup enables the RL policy to learn safely and directly on mobile robots in a real-world indoor environment, minimizing actual crashes even during training. Our real-world experiments show that, when compared with several baselines, our approach enjoys a higher average speed, lower crash rate, less emergency intervention, smaller computation overhead, and smoother overall control.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 23 Sep 2022.
Builds on
20 of 44 references.
References · 20
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2017Constrained Policy Optimizationcited by 983
- 2017End-to-end Driving via Conditional Imitation Learningcited by 485
- 2017Safe Reinforcement Learning via Shieldingcited by 449
- 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
- 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 233
- 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 102
- 2018Driving Policy Transfer via Modularity and Abstractioncited by 92
- 2017Uncertainty-Aware Reinforcement Learning for Collision Avoidancecited by 88
- 2017Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigationcited by 77
- 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
- 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 75
8 more
- 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 61
- 2019Deep Visual MPC-Policy Learning for Navigationcited by 56
- 2017Learning to Fly by Crashingcited by 41
- 2017Optimization-Based Collision Avoidancecited by 29
- 2020LaND: Learning to Navigate from Disengagementscited by 25
- 2021Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environmentscited by 12
- 2019Dynamic Channel: A Planning Framework for Crowd Navigationcited by 10
- 2021Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learningcited by 4
Built on by
Citing papers per year: 2024: 2.
2 papers.