Corpus ID: 278138

Traversing Environments Using Possibility Graphs with Multiple Action Types

  title={Traversing Environments Using Possibility Graphs with Multiple Action Types},
  author={Michael X. Grey and C. Karen Liu and A. Ames},
Locomotion for legged robots poses considerable challenges when confronted by obstacles and adverse environments. Footstep planners are typically only designed for one mode of locomotion, but traversing unfavorable environments may require several forms of locomotion to be sequenced together, such as walking, crawling, and jumping. Multi-modal motion planners can be used to address some of these problems, but existing implementations tend to be time-consuming and are limited to quasi-static… Expand
1 Citations
Long-horizon humanoid navigation planning using traversability estimates and previous experience
This paper presents a method that plans a torso guiding path which accounts for the difficulty of traversing the environment as predicted by learned regressors and decomposes the guiding path into a set of segments, each of which is assigned a motion mode and a planning method. Expand


Footstep and Motion Planning in Semi-unstructured Environments Using Possibility Graphs
This work introduces a planning method, called the “Possibility Graph”, which uses high-level approximations of constraint manifolds to rapidly explore the "possibility” of actions, thereby allowing lower-level motion planners to be utilized more efficiently. Expand
Footstep planning among obstacles for biped robots
  • J. Kuffner, K. Nishiwaki, S. Kagami, M. Inaba, H. Inoue
  • Engineering, Computer Science
  • Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180)
  • 2001
This work presents an algorithm for planning safe navigation strategies for biped robots moving in obstacle-cluttered environments that takes into account the unique ability of legged robots such as bipedal humanoids to traverse obstacles by stepping over them. Expand
Planning Biped Navigation Strategies in Complex Environments
We present an algorithm for planning goal-directed footstep navigation strategies for biped robots through obstacle-filled environ- ments and uneven ground. Planning footsteps is more general thanExpand
Humanoid manipulation planning using backward-forward search
This paper presents a hybrid planning system which is able to scale well for complex tasks without relying on predetermined robot actions, and utilizes the hybrid backward-forward planning algorithm for high-level task planning combined with humanoid primitives for standing and walking motion planning. Expand
Humanoid navigation with dynamic footstep plans
The problem of footstep planning for humanoid robots is formulated so that it can be solved with the incremental heuristic search method D* Lite and extensions are presented, including continuous footstep locations and efficient collision checking for footsteps. Expand
Randomized multi-modal motion planning for a humanoid robot manipulation task
This paper presents a highly general algorithm, Random-MMP, that repeatedly attempts mode switches sampled at random and applies the planner to a manipulation task on the Honda humanoid robot, where the robot is asked to push an object to a desired location on a cluttered table. Expand
Anytime search-based footstep planning with suboptimality bounds
This work proposes anytime search-based planning using the anytime repairing A* (ARA*) and randomized A * (R*) planners, which create paths that are goal-directed and guaranteed to be no more than a certain factor longer than the optimal solution. Expand
Online footstep planning for humanoid robots
An online algorithm for planning sequences of footstep locations that encode goal-directed navigation strategies for humanoid robots and results from an experimental implementation of the algorithm running on the H7 humanoid robot are shown. Expand
Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot
This paper describes a collection of optimization algorithms for achieving dynamic planning, control, and state estimation for a bipedal robot designed to operate reliably in complex environments and presents a state estimator formulation that permits highly precise execution of extended walking plans over non-flat terrain. Expand
Fast Humanoid Robot Collision-Free Footstep Planning Using Swept Volume Approximations
A novel and coherent framework for fast footstep planning for legged robots on a flat ground with 3-D obstacle avoidance is proposed, in which a rapidly exploring random tree variant is used to find collision-free sequences of half-steps (which are produced by a specific walking pattern generator). Expand