Interactive gibson benchmark: A benchmark for interactive navigation in cluttered environments
We present Interactive Gibson Benchmark, the first comprehensive benchmark for training
and evaluating Interactive Navigation solutions. Interactive Navigation tasks are robot …
and evaluating Interactive Navigation solutions. Interactive Navigation tasks are robot …
Combined task and motion planning through an extensible planner-independent interface layer
The need for combined task and motion planning in robotics is well understood. Solutions to
this problem have typically relied on special purpose, integrated implementations of task …
this problem have typically relied on special purpose, integrated implementations of task …
Integrated task and motion planning in belief space
LP Kaelbling, T Lozano-Pérez - The International Journal of …, 2013 - journals.sagepub.com
We describe an integrated strategy for planning, perception, state estimation and action in
complex mobile manipulation domains based on planning in the belief space of probability …
complex mobile manipulation domains based on planning in the belief space of probability …
[PDF][PDF] Incremental task and motion planning: A constraint-based approach.
We present a new algorithm for task and motion planning (TMP) and discuss the
requirements and abstractions necessary to obtain robust solutions for TMP in general. Our …
requirements and abstractions necessary to obtain robust solutions for TMP in general. Our …
An incremental constraint-based framework for task and motion planning
NT Dantam, ZK Kingston… - … Journal of Robotics …, 2018 - journals.sagepub.com
We present a new constraint-based framework for task and motion planning (TMP). Our
approach is extensible, probabilistically complete, and offers improved performance and …
approach is extensible, probabilistically complete, and offers improved performance and …
Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators
Most common navigation tasks in human environments require auxiliary arm interactions, eg
opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks …
opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks …
[PDF][PDF] Dealing with Difficult Instances of Object Rearrangement.
A Krontiris, KE Bekris - Robotics: Science and Systems, 2015 - researchgate.net
Rearranging multiple objects is a critical skill for robots so that they can effectively deal with
clutter in human spaces. This is a challenging problem as it involves combinatorially large …
clutter in human spaces. This is a challenging problem as it involves combinatorially large …
Spatial action maps for mobile manipulation
Typical end-to-end formulations for learning robotic navigation involve predicting a small set
of steering command actions (eg, step forward, turn left, turn right, etc.) from images of the …
of steering command actions (eg, step forward, turn left, turn right, etc.) from images of the …
Fast high-quality tabletop rearrangement in bounded workspace
In this paper, we examine the problem of rearranging many objects on a tabletop in a
cluttered setting using overhand grasps. Efficient solutions for the problem, which capture a …
cluttered setting using overhand grasps. Efficient solutions for the problem, which capture a …
Efficiently solving general rearrangement tasks: A fast extension primitive for an incremental sampling-based planner
A Krontiris, KE Bekris - 2016 IEEE International Conference on …, 2016 - ieeexplore.ieee.org
Manipulating multiple movable obstacles is a hard problem that involves searching high-
dimensional C-spaces. A milestone method for this problem was able to compute solutions …
dimensional C-spaces. A milestone method for this problem was able to compute solutions …