Reinforcement Learning with Non-uniform State Representations for Adaptive Search

06/15/2019
by   Sandeep Manjanna, et al.
0

Efficient spatial exploration is a key aspect of search and rescue. In this paper, we present a search algorithm that generates efficient trajectories that optimize the rate at which probability mass is covered by a searcher. This should allow an autonomous vehicle find one or more lost targets as rapidly as possible. We do this by performing non-uniform sampling of the search region. The path generated minimizes the expected time to locate the missing target by visiting high probability regions using non-myopic path generation based on reinforcement learning. We model the target probability distribution using a classic mixture of Gaussians model with means and mixture coefficients tuned according to the location and time of sightings of the lost target. Key features of our search algorithm are the ability to employ a very general non-deterministic action model and the ability to generate action plans for any new probability distribution using the parameters learned on other similar looking distributions. One of the key contributions of this paper is the use of non-uniform state aggregation for policy search in the context of robotics.

READ FULL TEXT

page 1

page 4

page 5

research
10/24/2018

Minsum k-Sink Problem on Path Networks

We consider the problem of locating a set of k sinks on a path network w...
research
07/29/2020

Non-Uniform Sampling of Fixed Margin Uniform Matrices

Data sets in the form of binary matrices are ubiquitous across scientifi...
research
04/28/2019

Real-time Trajectory Generation for Quadrotors using B-spline based Non-uniform Kinodynamic Search

In this paper, we propose a time-efficient approach to generate safe, sm...
research
06/18/2019

Convergence of the Non-Uniform Directed Physarum Model

The directed Physarum dynamics is known to solve positive linear program...
research
04/28/2020

A System for Generating Non-Uniform Random Variates using Graphene Field-Effect Transistors

We introduce a new method for hardware non-uniform random number generat...
research
04/21/2021

Exploiting Learned Policies in Focal Search

Recent machine-learning approaches to deterministic search and domain-in...
research
08/05/2020

A Probabilistic Model for Planar Sliding of Objects with Unknown Material Properties: Identification and Robust Planning

This paper introduces a new technique for learning probabilistic models ...

Please sign up or login with your details

Forgot password? Click here to reset