Learning to Predict Action Feasibility for Task and Motion Planning in 3D Environments - LAAS - Laboratoire d'Analyse et d'Architecture des Systèmes Access content directly
Conference Papers Year : 2023

Learning to Predict Action Feasibility for Task and Motion Planning in 3D Environments

Smail Ait Bouhsain
Rachid Alami
Thierry Simeon

Abstract

In Task and motion planning (TAMP), symbolic search is combined with continuous geometric planning. A task planner finds an action sequence while a motion planner checks its feasibility and plans the corresponding sequence of motions. However, due to the high combinatorial complexity of discrete search, the number of calls to the geometric planner can be very large. Previous works [1] [2] leverage learning methods to efficiently predict the feasibility of actions, much like humans do, on tabletop scenarios. This way, the time spent on motion planning can be greatly reduced. In this work, we generalize these methods to 3D environments, thus covering the whole workspace of the robot. We propose an efficient method for 3D scene representation, along with a deep neural network capable of predicting the probability of feasibility of an action. We develop a simple TAMP algorithm that integrates the trained classifier, and demonstrate the performance gain of using our approach on multiple problem domains. On complex problems, our method can reduce the time spent on geometric planning by up to 90%. Index Terms—Task and motion planning, 3D scene represen- tation, Action feasibility prediction, Deep learning
Fichier principal
Vignette du fichier
Neural_Feasibility_Prediction__Estimating_action_feasibility_for_guiding_TAMP.pdf (1.79 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03808885 , version 1 (10-10-2022)
hal-03808885 , version 2 (06-03-2023)

Identifiers

  • HAL Id : hal-03808885 , version 1

Cite

Smail Ait Bouhsain, Rachid Alami, Thierry Simeon. Learning to Predict Action Feasibility for Task and Motion Planning in 3D Environments. 2023 IEEE International Conference on Robotics and Automation (ICRA), May 2023, London, United Kingdom. ⟨hal-03808885v1⟩
28 View
25 Download

Share

Gmail Facebook Twitter LinkedIn More