Curriculum Learning for Safe Mapless Navigation

TL;DR

This paper demonstrates that Curriculum Learning combined with Transfer of Learning enhances the safety and success rate of robot mapless navigation, reducing collisions and improving policy reliability compared to standard end-to-end training.

Contribution

It introduces a CL approach utilizing ToL and fine-tuning in simulation, showing improved safety and success rates over traditional methods.

Findings

10% fewer collisions in unseen scenarios

Enhanced safety and success rate with CL and ToL

Formal verification confirms improved policy correctness

Abstract

This work investigates the effects of Curriculum Learning (CL)-based approaches on the agent's performance. In particular, we focus on the safety aspect of robotic mapless navigation, comparing over a standard end-to-end (E2E) training strategy. To this end, we present a CL approach that leverages Transfer of Learning (ToL) and fine-tuning in a Unity-based simulation with the Robotnik Kairos as a robotic agent. For a fair comparison, our evaluation considers an equal computational demand for every learning approach (i.e., the same number of interactions and difficulty of the environments) and confirms that our CL-based method that uses ToL outperforms the E2E methodology. In particular, we improve the average success rate and the safety of the trained policy, resulting in 10% fewer collisions in unseen testing scenarios. To further confirm these results, we employ a formal verification tool to quantify the number of correct behaviors of Reinforcement Learning policies over desired specifications.