Traversability-Aware Legged Navigation by Learning from Real-World Visual Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hongbo, Li, Zhongyu, Zeng, Xuanqi, Smith, Laura, Stachowicz, Kyle, Shah, Dhruv, Yue, Linzhu, Song, Zhitao, Xia, Weipeng, Levine, Sergey, Sreenath, Koushil, Liu, Yun-hui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909385383477248
author Zhang, Hongbo
Li, Zhongyu
Zeng, Xuanqi
Smith, Laura
Stachowicz, Kyle
Shah, Dhruv
Yue, Linzhu
Song, Zhitao
Xia, Weipeng
Levine, Sergey
Sreenath, Koushil
Liu, Yun-hui
author_facet Zhang, Hongbo
Li, Zhongyu
Zeng, Xuanqi
Smith, Laura
Stachowicz, Kyle
Shah, Dhruv
Yue, Linzhu
Song, Zhitao
Xia, Weipeng
Levine, Sergey
Sreenath, Koushil
Liu, Yun-hui
contents The enhanced mobility brought by legged locomotion empowers quadrupedal robots to navigate through complex and unstructured environments. However, optimizing agile locomotion while accounting for the varying energy costs of traversing different terrains remains an open challenge. Most previous work focuses on planning trajectories with traversability cost estimation based on human-labeled environmental features. However, this human-centric approach is insufficient because it does not account for the varying capabilities of the robot locomotion controllers over challenging terrains. To address this, we develop a novel traversability estimator in a robot-centric manner, based on the value function of the robot's locomotion controller. This estimator is integrated into a new learning-based RGBD navigation framework. The framework employs multiple training stages to develop a planner that guides the robot in avoiding obstacles and hard-to-traverse terrains while reaching its goals. The training of the navigation planner is directly performed in the real world using a sample efficient reinforcement learning method that utilizes both online data and offline datasets. Through extensive benchmarking, we demonstrate that the proposed framework achieves the best performance in accurate traversability cost estimation and efficient learning from multi-modal data (including the robot's color and depth vision, as well as proprioceptive feedback) for real-world training. Using the proposed method, a quadrupedal robot learns to perform traversability-aware navigation through trial and error in various real-world environments with challenging terrains that are difficult to classify using depth vision alone. Moreover, the robot demonstrates the ability to generalize the learned navigation skills to unseen scenarios. Video can be found at https://youtu.be/RSqnIWZ1qks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
Zhang, Hongbo
Li, Zhongyu
Zeng, Xuanqi
Smith, Laura
Stachowicz, Kyle
Shah, Dhruv
Yue, Linzhu
Song, Zhitao
Xia, Weipeng
Levine, Sergey
Sreenath, Koushil
Liu, Yun-hui
Robotics
The enhanced mobility brought by legged locomotion empowers quadrupedal robots to navigate through complex and unstructured environments. However, optimizing agile locomotion while accounting for the varying energy costs of traversing different terrains remains an open challenge. Most previous work focuses on planning trajectories with traversability cost estimation based on human-labeled environmental features. However, this human-centric approach is insufficient because it does not account for the varying capabilities of the robot locomotion controllers over challenging terrains. To address this, we develop a novel traversability estimator in a robot-centric manner, based on the value function of the robot's locomotion controller. This estimator is integrated into a new learning-based RGBD navigation framework. The framework employs multiple training stages to develop a planner that guides the robot in avoiding obstacles and hard-to-traverse terrains while reaching its goals. The training of the navigation planner is directly performed in the real world using a sample efficient reinforcement learning method that utilizes both online data and offline datasets. Through extensive benchmarking, we demonstrate that the proposed framework achieves the best performance in accurate traversability cost estimation and efficient learning from multi-modal data (including the robot's color and depth vision, as well as proprioceptive feedback) for real-world training. Using the proposed method, a quadrupedal robot learns to perform traversability-aware navigation through trial and error in various real-world environments with challenging terrains that are difficult to classify using depth vision alone. Moreover, the robot demonstrates the ability to generalize the learned navigation skills to unseen scenarios. Video can be found at https://youtu.be/RSqnIWZ1qks.
title Traversability-Aware Legged Navigation by Learning from Real-World Visual Data
topic Robotics
url https://arxiv.org/abs/2410.10621