TY - GEN
T1 - Ving
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
AU - Shah, Dhruv
AU - Eysenbach, Benjamin
AU - Kahn, Gregory
AU - Rhinehart, Nicholas
AU - Levine, Sergey
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - We propose a learning-based navigation system for reaching visually indicated goals and demonstrate this system on a real mobile robot platform. Learning provides an appealing alternative to conventional methods for robotic navigation: instead of reasoning about environments in terms of geometry and maps, learning can enable a robot to learn about navigational affordances, understand what types of obstacles are traversable (e.g., tall grass) or not (e.g., walls), and generalize over patterns in the environment. However, unlike conventional planning algorithms, it is harder to change the goal for a learned policy during deployment. We propose a method for learning to navigate towards a goal image of the desired destination. By combining a learned policy with a topological graph constructed out of previously observed data, our system can determine how to reach this visually indicated goal even in the presence of variable appearance and lighting. Three key insights, waypoint proposal, graph pruning and negative mining, enable our method to learn to navigate in real-world environments using only offline data, a setting where prior methods struggle. We instantiate our method on a real outdoor ground robot and show that our system, which we call ViNG, outperforms previously-proposed methods for goal-conditioned reinforcement learning, including other methods that incorporate reinforcement learning and search. We also study how ViNG generalizes to unseen environments and evaluate its ability to adapt to such an environment with growing experience. Finally, we demonstrate ViNG on a number of real-world applications, such as last-mile delivery and warehouse inspection. We encourage the reader to visit the project website for videos of our experiments and demonstrations.
AB - We propose a learning-based navigation system for reaching visually indicated goals and demonstrate this system on a real mobile robot platform. Learning provides an appealing alternative to conventional methods for robotic navigation: instead of reasoning about environments in terms of geometry and maps, learning can enable a robot to learn about navigational affordances, understand what types of obstacles are traversable (e.g., tall grass) or not (e.g., walls), and generalize over patterns in the environment. However, unlike conventional planning algorithms, it is harder to change the goal for a learned policy during deployment. We propose a method for learning to navigate towards a goal image of the desired destination. By combining a learned policy with a topological graph constructed out of previously observed data, our system can determine how to reach this visually indicated goal even in the presence of variable appearance and lighting. Three key insights, waypoint proposal, graph pruning and negative mining, enable our method to learn to navigate in real-world environments using only offline data, a setting where prior methods struggle. We instantiate our method on a real outdoor ground robot and show that our system, which we call ViNG, outperforms previously-proposed methods for goal-conditioned reinforcement learning, including other methods that incorporate reinforcement learning and search. We also study how ViNG generalizes to unseen environments and evaluate its ability to adapt to such an environment with growing experience. Finally, we demonstrate ViNG on a number of real-world applications, such as last-mile delivery and warehouse inspection. We encourage the reader to visit the project website for videos of our experiments and demonstrations.
UR - http://www.scopus.com/inward/record.url?scp=85125505411&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125505411&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561936
DO - 10.1109/ICRA48506.2021.9561936
M3 - Conference contribution
AN - SCOPUS:85125505411
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 13215
EP - 13222
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 30 May 2021 through 5 June 2021
ER -