Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation

2017/03/01 by Lei Tai, Giuseppe Paolo, Tai, Lei +3 · 24 citations
Computer Science · Engineering · #Reinforcement Learning in Robotics #Robotic Locomotion and Control #Robotic Path Planning Algorithms #cs.AI #cs.LG #cs.RO

paper · pdf · doi:10.48550/arxiv.1703.00420

video: https://www.youtube.com/watch?v=9AOIwBYIBbs, 6 pages, 9 figures, to appear in he 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017), final submission version

arxiv created 2017/07/21 · arxiv updated 2017/07/24

Abstract

We present a learning-based mapless motion planner by taking the sparse 10-dimensional range findings and the target position with respect to the mobile robot coordinate frame as input and the continuous steering commands as output. Traditional motion planners for mobile ground robots with a laser range sensor mostly depend on the obstacle map of the navigation environment where both the highly precise laser sensor and the obstacle map building work of the environment are indispensable. We show that, through an asynchronous deep reinforcement learning method, a mapless motion planner can be trained end-to-end without any manually designed features and prior demonstrations. The trained planner can be directly applied in unseen virtual and real environments. The experiments show that the proposed mapless motion planner can navigate the nonholonomic mobile robot to the desired targets without colliding with any obstacles.

Cited by

• Tiny, On-Device Decision Makers with the MiniConv Library
• Nonholonomic Narrow Dead-End Escape with Deep Reinforcement Learning
• Improved adaptive wind driven optimization algorithm for real-time path planning
• Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments
• Adaptive Trajectory Refinement for Optimization-based Local Planning in Narrow Passages
• Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning
• Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning
• The Reality Gap in Robotics: Challenges, Solutions, and Best Practices
• Learning from Hallucinating Critical Points for Navigation in Dynamic Environments
• CrowdMove: Autonomous Mapless Navigation in Crowded Scenarios
• Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal
• A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation
• Hierarchical Deep Deterministic Policy Gradient for Autonomous Maze Navigation of Mobile Robots
• DiWA: Diffusion Policy Adaptation with World Models
• CogniPlan: Uncertainty-Guided Path Planning with Conditional Generative Layout Prediction
• Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
• The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual Navigation
• RRT* Combined with GVO for Real-time Nonholonomic Robot Navigation in Dynamic Environment
• Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation
• General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting
• Probabilistic Collision Risk Estimation for Pedestrian Navigation
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Parameter Sharing Reinforcement Learning Architecture for Multi Agent Driving Behaviors
• Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning

Related

• Parallel Distributional Deep Reinforcement Learning for Mapless Navigation of Terrestrial Mobile Robots
• Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environments
• Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems
• Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation
• Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player