Reward-Based Collision-Free Algorithm for Trajectory Planning of Autonomous Robots

TL;DR

This paper introduces a reward-based, collision-free trajectory planning algorithm for autonomous robots that optimizes waypoint sequences using a genetic algorithm, ensuring obstacle avoidance, dynamic feasibility, and mission constraints.

Contribution

It extends the prize-collecting TSP with a novel genetic algorithm incorporating differential flatness and clothoid curves for feasible, smooth trajectories.

Findings

Effective in simulation and real experiments with ground vehicle, quadrotor, quadruped

Outperforms traditional methods in obstacle avoidance and trajectory smoothness

Validated through benchmarking and time-complexity analysis

Abstract

This paper proposes a novel mission planning algorithm for autonomous robots that selects an optimal waypoint sequence from a predefined set to maximize total reward while satisfying obstacle avoidance, state, input, derivative, mission time, and distance constraints. The formulation extends the prize-collecting traveling salesman problem. A tailored genetic algorithm evolves candidate solutions using a fitness function, crossover, and mutation, with constraint enforcement via a penalty method. Differential flatness and clothoid curves are employed to penalize infeasible trajectories efficiently, while the Euler spiral method ensures curvature-continuous trajectories with bounded curvature, enhancing dynamic feasibility and mitigating oscillations typical of minimum-jerk and snap parameterizations. Due to the discrete variable length optimization space, crossover is performed using a dynamic time-warping-based method and extended convex combination with projection. The algorithm's performance is validated through simulations and experiments with a ground vehicle, quadrotor, and quadruped, supported by benchmarking and time-complexity analysis.