Reactive Collision Avoidance using Evolutionary Neural Networks

TL;DR

This paper presents a novel reactive collision avoidance method for vehicles using evolutionary neural networks trained with a single rangefinder sensor, validated through extensive simulation experiments demonstrating good generalization.

Contribution

The paper introduces a new ENN-based collision avoidance approach that requires only one sensor and demonstrates its effectiveness and adaptability in various simulated scenarios.

Findings

Successfully learned collision avoidance in static tracks

Sensor resolution impacts learning process

Generalizes to different sensors and tasks

Abstract

Collision avoidance systems can play a vital role in reducing the number of accidents and saving human lives. In this paper, we introduce and validate a novel method for vehicles reactive collision avoidance using evolutionary neural networks (ENN). A single front-facing rangefinder sensor is the only input required by our method. The training process and the proposed method analysis and validation are carried out using simulation. Extensive experiments are conducted to analyse the proposed method and evaluate its performance. Firstly, we experiment the ability to learn collision avoidance in a static free track. Secondly, we analyse the effect of the rangefinder sensor resolution on the learning process. Thirdly, we experiment the ability of a vehicle to individually and simultaneously learn collision avoidance. Finally, we test the generality of the proposed method. We used a more realistic and powerful simulation environment (CarMaker), a camera as an alternative input sensor, and lane keeping as an extra feature to learn. The results are encouraging; the proposed method successfully allows vehicles to learn collision avoidance in different scenarios that are unseen during training. It also generalizes well if any of the input sensor, the simulator, or the task to be learned is changed.