Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning

08/02/2021
by   Kevin Osanlou, et al.
0

Learning-based methods are increasingly popular for search algorithms in single-criterion optimization problems. In contrast, for multiple-criteria optimization there are significantly fewer approaches despite the existence of numerous applications. Constrained path-planning for Autonomous Ground Vehicles (AGV) is one such application, where an AGV is typically deployed in disaster relief or search and rescue applications in off-road environments. The agent can be faced with the following dilemma : optimize a source-destination path according to a known criterion and an uncertain criterion under operational constraints. The known criterion is associated to the cost of the path, representing the distance. The uncertain criterion represents the feasibility of driving through the path without requiring human intervention. It depends on various external parameters such as the physics of the vehicle, the state of the explored terrains or weather conditions. In this work, we leverage knowledge acquired through offline simulations by training a neural network model to predict the uncertain criterion. We integrate this model inside a path-planner which can solve problems online. Finally, we conduct experiments on realistic AGV scenarios which illustrate that the proposed framework requires human intervention less frequently, trading for a limited increase in the path distance.

READ FULL TEXT
research
08/02/2021

Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search

Learning-based methods are growing prominence for planning purposes. How...
research
10/14/2021

Integrated Path Planning and Tracking Control of Marine Current Turbine in Uncertain Ocean Environments

This paper presents an integrated path planning and tracking control of ...
research
01/19/2020

Optimization-Based On-Road Path Planning for Articulated Vehicles

Maneuvering an articulated vehicle on narrow road stretches is often a c...
research
09/17/2019

Real-time Multi-target Path Prediction and Planning for Autonomous Driving aided by FCN

Real-time multi-target path planning is a key issue in the field of auto...
research
12/01/2022

Path Planning Problem under non-probabilistic Uncertainty

This paper considers theoretical solutions for path planning problems un...
research
04/23/2021

Risk-Aware Path Planning for Ground Vehicles using Occluded Aerial Images

We consider scenarios where a ground vehicle plans its path using data g...

Please sign up or login with your details

Forgot password? Click here to reset