ViTAL: Vision-Based Terrain-Aware Locomotion for Legged Robots

Abstract

This work is on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot may end up in a state with no reachable safe footholds. Therefore, we present a Vision-Based Terrain-Aware Locomotion (ViTAL) strategy that consists of novel pose adaptation and foothold selection algorithms. ViTAL introduces a different paradigm in pose adaptation that does not optimize the body pose relative to given footholds, but the body pose that maximizes the chances of the legs in reaching safe footholds. ViTAL plans footholds and poses based on skills that characterize the robot's capabilities and its terrain-awareness. We use the 90 kg HyQ and 140 kg HyQReal quadruped robots to validate ViTAL, and show that they are able to climb various obstacles including stairs, gaps, and rough terrains at different speeds and gaits. We compare ViTAL with a baseline strategy that selects the robot pose based on given selected footholds, and show that ViTAL outperforms the baseline.

IEEE Transactions on Robotics, 2022. part of dissertation arXiv:2212.00683

References in corpus (11)

• Learning Quadrupedal Locomotion over Challenging Terrain
• Learning robust perceptive locomotion for quadrupedal robots in the wild
• Multi-expert learning of adaptive legged locomotion
• Motion Planning for Quadrupedal Locomotion: Coupled Planning, Terrain Mapping and Whole-Body Control
• Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
• Model Hierarchy Predictive Control of Robotic Systems
• Efficient Multi-Contact Pattern Generation with Sequential Convex Approximations of the Centroidal Dynamics
• Navigating by Touch: Haptic Monte Carlo Localization via Geometric Sensing and Terrain Classification
• Single-shot Foothold Selection and Constraint Evaluation for Quadruped Locomotion
• Haptic Sequential Monte Carlo Localization for Quadrupedal Locomotion in Vision-Denied Scenarios
• On Terrain-Aware Locomotion for Legged Robots

Cited by in corpus (4)

• Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Control
• Quadrupedal Footstep Planning using Learned Motion Models of a Black-Box Controller
• Seq-DeepIPC: Sequential Sensing for End-to-End Control in Legged Robot Navigation
• LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mamba