Curriculum Learning for Safe Mapless Navigation
arXiv:2112.12490 · doi:10.1145/3477314.3507182
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.
arXiv comment8 pages, 5 figures. The poster version of this paper has been accepted by The 37th ACM/SIGAPP Symposium on Applied Computing Proceedings (SAC IRMAS 2022)
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Trust Region Policy Optimization
- Solving Rubik's Cube with a Robot Hand
- Unity: A General Platform for Intelligent Agents
- From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
- Formal Security Analysis of Neural Networks using Symbolic Intervals
- Benchmarking Batch Deep Reinforcement Learning Algorithms
- Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning
- A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms