Real-time Motion Planning in Unknown Environments for Legged Robotic Planetary Exploration

Albee, Keenan; Hernandez, Alejandro Cabrales; Jia-Richards, Oliver; Espinoza, Antonio Terán

doi:10.1109/aero47225.2020.9172596

Cited by 4 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our problem is partially observable because of the limited sensors onboard the robot 1 . The robot is equipped with a LiDAR sensor to perceive the distances d to the surrounding environment.…”

Section: A Multi-task Reinforcement Learning Formulationmentioning

confidence: 99%

“…The ability to traverse unstructured terrains make legged robots an appealing solution to a wide variety of tasks, including disaster relief, last-mile delivery, industrial inspection, and planetary exploration [1], [2]. To deploy robots in these settings successfully, we must design controllers that work well across many different terrains.…”

Section: Introductionmentioning

confidence: 99%

“…We call this parameterization a visual-locomotion policy. While many 1 Google Brain Robotics, {georgeyu,pengxu,atil,jietan}@google.com 2 Georgia Institute of Technology, aescontrela@gatech.edu Work performed while Alejandro was an intern at Google Brain. prior works in the legged robot literature focused on blind walking, which does not involve exteroceptive sensors (e.g., camera, LiDAR), we find that exteroceptive perception is essential for robots to navigate in diverse environments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Zero-Shot Terrain Generalization for Visual Locomotion Policies

Escontrela¹,

Yu²,

Xu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of environments. In this paper, we address this challenge of automatically learning locomotion controllers that can generalize to a diverse collection of terrains often encountered in the real world. We frame this challenge as a multi-task reinforcement learning problem and define each task as a type of terrain that the robot needs to traverse. We propose an end-to-end learning approach that makes direct use of the raw exteroceptive inputs gathered from a simulated 3D LiDAR sensor, thus circumventing the need for ground-truth heightmaps or preprocessing of perception information. As a result, the learned controller demonstrates excellent zeroshot generalization capabilities and can navigate 13 different environments, including stairs, rugged land, cluttered offices, and indoor spaces with humans.

show abstract

Section: A Multi-task Reinforcement Learning Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation