AvoidBench: A high-fidelity vision-based obstacle avoidance benchmarking suite for multi-rotors

TL;DR

AvoidBench is a comprehensive benchmarking suite for evaluating vision-based obstacle avoidance algorithms on multi-rotor drones using high-fidelity simulation and real-world validation.

Contribution

It introduces a high-fidelity simulation platform with performance and environment metrics for fair comparison of obstacle avoidance algorithms.

Findings

Validated simulation results with real-world experiments

Compared three obstacle avoidance algorithms under various conditions

Provided insights into algorithm suitability for different environments

Abstract

Obstacle avoidance is an essential topic in the field of autonomous drone research. When choosing an avoidance algorithm, many different options are available, each with their advantages and disadvantages. As there is currently no consensus on testing methods, it is quite challenging to compare the performance between algorithms. In this paper, we propose AvoidBench, a benchmarking suite which can evaluate the performance of vision-based obstacle avoidance algorithms by subjecting them to a series of tasks. Thanks to the high fidelity of multi-rotors dynamics from RotorS and virtual scenes of Unity3D, AvoidBench can realize realistic simulated flight experiments. Compared to current drone simulators, we propose and implement both performance and environment metrics to reveal the suitability of obstacle avoidance algorithms for environments of different complexity. To illustrate AvoidBench's usage, we compare three algorithms: Ego-planner, MBPlanner, and Agile-autonomy. The trends observed are validated with real-world obstacle avoidance experiments.