Efficient Simultaneous Motion and Task Planning Using Task Reachability Graphs
Advisor Information
Prithviraj Dasgupta
Location
UNO Criss Library, Room 232
Presentation Type
Oral Presentation
Start Date
6-3-2015 11:00 AM
End Date
6-3-2015 11:15 AM
Abstract
We consider the problem where robots are provided with a set of task locations to visit in an environment of known size, but the length of the path between a pair of task locations is initially known only coarsely by the robots. The objective of the robots is to find the order of tasks that reduces the path length (or, energy expended) to visit the task locations in such a scenario. To solve this problem, we propose an abstraction called a task reachability graph (TRG) that integrates the task ordering with the path planning by the robots. The TRG is updated dynamically based on inter-task path costs calculated using a sampling-based path planner, and, a Hidden Markov Model (HMM)-based technique that calculates the belief in the current path costs based on the environment perceived by the robot's sensors. We then describe a Markov Decision Process (MDP)-based algorithm that can be used by each robot in a distributed manner to reason about the path lengths between tasks using the currently available path information, and select the paths that reduce the overall path length to visit the task locations. We have evaluated our algorithm on simulated Corobot robots within different environments while varying the number of task locations, obstacle geometries and number of robots. Our results show that the TRG-based approach performs up to 40% better in terms of distances traveled, 77% fewer replans, 76% less planning and locomotion times, as compared to a greedy, nearest-task-first selection algorithm.
Efficient Simultaneous Motion and Task Planning Using Task Reachability Graphs
UNO Criss Library, Room 232
We consider the problem where robots are provided with a set of task locations to visit in an environment of known size, but the length of the path between a pair of task locations is initially known only coarsely by the robots. The objective of the robots is to find the order of tasks that reduces the path length (or, energy expended) to visit the task locations in such a scenario. To solve this problem, we propose an abstraction called a task reachability graph (TRG) that integrates the task ordering with the path planning by the robots. The TRG is updated dynamically based on inter-task path costs calculated using a sampling-based path planner, and, a Hidden Markov Model (HMM)-based technique that calculates the belief in the current path costs based on the environment perceived by the robot's sensors. We then describe a Markov Decision Process (MDP)-based algorithm that can be used by each robot in a distributed manner to reason about the path lengths between tasks using the currently available path information, and select the paths that reduce the overall path length to visit the task locations. We have evaluated our algorithm on simulated Corobot robots within different environments while varying the number of task locations, obstacle geometries and number of robots. Our results show that the TRG-based approach performs up to 40% better in terms of distances traveled, 77% fewer replans, 76% less planning and locomotion times, as compared to a greedy, nearest-task-first selection algorithm.