DeepAI
Log In Sign Up

Cooperative Motion Planning for Non-Holonomic Agents with Value Iteration Networks

09/15/2017
by   Eike Rehder, et al.
0

Cooperative motion planning is still a challenging task for robots. Recently, Value Iteration Networks (VINs) were proposed to model motion planning tasks as Neural Networks. In this work, we extend VINs to solve cooperative planning tasks under non-holonomic constraints. For this, we interconnect multiple VINs to pay respect to each other's outputs. Policies for cooperation are generated via iterative gradient descend. Validation in simulation shows that the resulting networks can resolve non-holonomic motion planning problems that require cooperation.

READ FULL TEXT

page 5

page 6

08/12/2020

Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots

Reliable real-time planning for robots is essential in today's rapidly e...
08/23/2017

Towards Cooperative Motion Planning for Automated Vehicles in Mixed Traffic

While motion planning techniques for automated vehicles in a reactive an...
09/14/2021

Designing Multi-Stage Coupled Convex Programming with Data-Driven McCormick Envelope Relaxations for Motion Planning

For multi-limbed robots, motion planning with posture and force constrai...
07/29/2022

Neural-Guided RuntimePrediction of Planners for Improved Motion and Task Planning with Graph Neural Networks

The past decade has amply demonstrated the remarkable functionality that...
07/11/2021

Entropy Regularized Motion Planning via Stein Variational Inference

Many Imitation and Reinforcement Learning approaches rely on the availab...
09/27/2018

Object Detection and Motion Planning for Automated Welding of Tubular Joints

Automatic welding of tubular TKY joints is an important and challenging ...
09/05/2019

A Lexicographic Search Method for Multi-Objective Motion Planning

We consider multi-objective motion planning problems in which two compet...