Maxim Likhachev

TL;DR: Multi-Heuristic A* MHA* as mentioned in this paper is a heuristic search that takes in multiple, arbitrarily inadmissible heuristics in addition to a single consistent heuristic, and uses all of them simultaneously to search in a way that preserves guarantees on completeness and bounds on sub-optimality.

TL;DR: This work addresses the problem of purposefully manipulating an articulated object, with uncertainty in the type of articulation, and provides an efficient planning algorithm and a representation for articulated objects called the Generalized Kinematic Graph (GK-Graph), that allows for modeling complex mechanisms whose articulation varies as a function of the state space.

TL;DR: This work extends MHA* to an anytime version by borrowing some of the concepts from Anytime Repairing A* (ARA*) that runs a series of Weighted A** (WA*) (Pohl 1970) searches, each with a decreasing weight on heuristics.

TL;DR: In this article, a planning, learning, and reasoning framework is proposed for real-time motion planning for a complex robotic system carrying two articulated mechanisms, an arm and a scooper, to autonomously unloading boxes from trucks using an industrial manipulator robot.

TL;DR: In this article, a computationally simple algorithm for these vehicles that determines simultaneous arrival paths from arbitrary starting points is presented, based on planar B-spline curves so that fully defined feasible trajectories can be quickly determined, compactly encoded, and precisely executed.