2018 IEEE International Conference on Robotics and Automation (ICRA) 2018
DOI: 10.1109/icra.2018.8461134
|View full text |Cite
|
Sign up to set email alerts
|

A Single-Planner Approach to Multi-Modal Humanoid Mobility

Abstract: In this work, we present an approach to planning for humanoid mobility. Humanoid mobility is a challenging problem, as the configuration space for a humanoid robot is intractably large, especially if the robot is capable of performing many types of locomotion. For example, a humanoid robot may be able to perform such tasks as bipedal walking, crawling, and climbing. Our approach is to plan for all these tasks within a single search process. This allows the search to reason about all the capabilities of the rob… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
4
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(4 citation statements)
references
References 17 publications
0
4
0
Order By: Relevance
“…Another related approach is adaptive dimensionality planning [9], where a single graph search is made on a hybrid state space with multiple lowdimensional subspaces, a high-level subspace, and mappings between them. The approach has been applied to legged robots for automatically planning over crawling, bipedal and climbing motions [10], although currently reported results have low planning success rates.…”
Section: Related Workmentioning
confidence: 99%
“…Another related approach is adaptive dimensionality planning [9], where a single graph search is made on a hybrid state space with multiple lowdimensional subspaces, a high-level subspace, and mappings between them. The approach has been applied to legged robots for automatically planning over crawling, bipedal and climbing motions [10], although currently reported results have low planning success rates.…”
Section: Related Workmentioning
confidence: 99%
“…Homotopy identification is easy for low resolution work spaces; however, the concept is extremely computationally expensive when applied directly on high dimensional configuration spaces. Dornbush et al showed a powerful capability of the planning techniques being able to solve for motion of a large degree‐of‐freedom humanoid showing walking, climbing, and crawling behaviors. However, reduction in the number of state variables and taking only the most relevant ones were done for each stage.…”
Section: Related Workmentioning
confidence: 99%
“…Thus, the system for motion synthesis has to offer a biologically inspired online modification of planned path and walking parameters and be supported by a robust motion control system that can compensate disturbances while constantly preserving dynamic balance. Path planner introduced by Dornbush et al (2018) decomposes the task into a sequence of smaller tasks and focuses the planning efforts to reason over much smaller search spaces. We find this is a human-like approach were local obstacles should be treated first, but always working on solving the main task.…”
Section: Introductionmentioning
confidence: 99%