LaND: Learning to Navigate From Disengagements

Consistently testing autonomous mobile robots in real world scenarios is a necessary aspect of developing autonomous navigation systems. Each time the human safety monitor disengages the robot's autonomy system due to the robot performing an undesirable maneuver, the autonomy developers gain in...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE robotics and automation letters Ročník 6; číslo 2; s. 1872 - 1879
Hlavní autori: Kahn, Gregory, Abbeel, Pieter, Levine, Sergey
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Autonomous navigation
Autonomy
Big data in robotics and automation
field robots
Learning
machine learning for robot control
Mobile robots
Navigation
Navigation systems
Neural networks
Predictive models
Reinforcement learning
Robot sensing systems
Robots
Testing
Testing time
Troubleshooting
Walkways
Websites
ISSN:2377-3766, 2377-3766
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Consistently testing autonomous mobile robots in real world scenarios is a necessary aspect of developing autonomous navigation systems. Each time the human safety monitor disengages the robot's autonomy system due to the robot performing an undesirable maneuver, the autonomy developers gain insight into how to improve the autonomy system. However, we believe that these disengagements not only show where the system fails, which is useful for troubleshooting, but also provide a direct learning signal by which the robot can learn to navigate. We present a reinforcement learning approach for learning to navigate from disengagements, or LaND. LaND learns a neural network model that predicts which actions lead to disengagements given the current sensory observation, and then at test time plans and executes actions that avoid disengagements. Our results demonstrate LaND can successfully learn to navigate in diverse, real world sidewalk environments, outperforming both imitation learning and reinforcement learning approaches. Videos, code, and other material are available on our website https://sites.google.com/view/sidewalk-learning .
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2021.3060404