Traversing challenging structures like boulders, rubble, stairs and steps, mobile robots need a special level of mobility. Robots with reconfigurable chassis are able to alter their configuration to overcome such structures. This paper presents a two-stage motion planning scheme for reconfigurable robots in rough terrain. First, we consider the robot’s operating limits rather than the complete ...

This paper addresses the problem of teaching a robot interaction behaviors using the imitation learning paradigm. Particularly, the approach makes use of Gaussian Mixture Models (GMMs) to model the physical interaction of the robot and the person when the robot is teleoperated or guided by an expert. The learned models are integrated into a sample-based planner, an RRT*, at two levels: as a cos...

After the boom of pharmacological research during the 1950s, mainly as a result of the screening technique, the identification of active molecules, their reshaping by means of pharmaco-chemical drug design, and the creation of extremely efficacious and successful medicines, the pharmaceutical world sought a new source of inspiration. Such biota as the tropical forest, a quantity of plants credi...

This paper proposes a sampling based planning algorithm to control autonomous vehicles. We propose an improved Rapidly-exploring Random Tree which includes the definition of Knearest points and propose a two-stage sampling strategy to adjust RRT in other to perform maneuver while avoiding collision. The simulation results show the success of the algorithm.

This paper summarizes our recent development of algorithms that construct feasible trajectories for problems that involve both differential constraints (typically in the form of an underactuated nonlinear system), and global constraints (typically arising from robot collisions). Dynamic programming approaches are described that produce approximately-optimal solutions for low-dimensional problem...

Randomized, sampling-based planning has a long history of success, and although the benefits associated with this use of randomization are widely-recognized, its costs are not well-understood. We examine a variety of problem instances solved with the Rapidly-exploring Random Tree algorithm, demonstrating that heavy-tailed runtime distributions are both common and potentially exploitable. We sho...

This paper presents an approach for optimal path planning on implicitly-defined configuration spaces such as those arising, for instance, when manipulating an object with two arms or with a multifingered hand. In this kind of situations, the kinematic and contact constraints induce configuration spaces that are manifolds embedded in higher dimensional ambient spaces. Existing sampling-based app...

This paper presents an interactive motion planning system to compute free collision motion in a numerical model. The system is based on interaction between a user and a motion planning algorithm. On one hand the user moves the object with an interactive device and on the other hand a motion planning algorithm searches a solution in the configuration space. The interaction aims at improving the ...

This document presents a demo storyboard for an accepted paper in the ICAPS 2011. The paper presents a method that builds a topological environment based on the workspace to compute homotopy classes, which topologically describe how paths go through the obstacles in the workspace. Then, the homotopy classes are sorted according to an heuristic estimation of their lower bound. Only those with sm...