Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning

Sampling-Based Motion Planning

Learning Sampling Distributions for Robot Motion Planning

A defining feature of sampling-based motion planning is the reliance on an implicit representation of the state space, which is enabled by a set of probing samples. Traditionally, these samples are drawn either probabilistically or deterministically to uniformly cover the state space. Yet, the motion of many robotic systems is often restricted to “small” regions of the state space, due to e.g. ...

Ego-Motion Computing for Vehicle Velocity Estimation

In this paper, we present a method for computing velocity using a single camera onboard a road vehicle, i.e. an automobile. The use of computer vision provides a reliable method to measure vehicle velocity based on egomotion computation. By doing so, cumulative errors inherent to odometrybased systems can be reduced to some extent. Road lane markings are the basic features used by the algorithm...

Nonholonomic motion planning for car-like robots

We consider the robot motion planning problem in the presence of non-integrable kinematic constraints, known as non-holonomic constraints. Car-like non-holonomic mobile robots are used for solving this problem, and several implemented planners are discussed. We claim that the randomized methods are more capable of efficiently solving many challenging, high-dimensional problems. Results with ran...

Nonholonomic Motion Planning for Mobile Manipulators

|A nonholonomic motion planner for mobile manipulators moving in cluttered environments is presented. The approach is based on a discontinous feedback law under the infuence of a special potential eld. Convergence is shown via Lyapunov's direct method. Utilizing redundancy, the methodology allows the system to perform secondary, connguration dependent, objectives such as singularity avoidance. ...