Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environments
This work addresses the challenge of reliable navigation for autonomous systems in real-world, sensor-impaired conditions, though it is incremental as it benchmarks existing methods and adds adversarial training.
The paper tackled the problem of autonomous navigation in environments with sensor noise and denial by benchmarking deep reinforcement learning algorithms, showing that DreamerV3 outperforms other methods in visual navigation tasks with dynamic goals and sensor denial, and adversarial training improved robustness in denied environments at a cost in vanilla settings.
Deep Reinforcement learning (DRL) is used to enable autonomous navigation in unknown environments. Most research assume perfect sensor data, but real-world environments may contain natural and artificial sensor noise and denial. Here, we present a benchmark of both well-used and emerging DRL algorithms in a navigation task with configurable sensor denial effects. In particular, we are interested in comparing how different DRL methods (e.g. model-free PPO vs. model-based DreamerV3) are affected by sensor denial. We show that DreamerV3 outperforms other methods in the visual end-to-end navigation task with a dynamic goal - and other methods are not able to learn this. Furthermore, DreamerV3 generally outperforms other methods in sensor-denied environments. In order to improve robustness, we use adversarial training and demonstrate an improved performance in denied environments, although this generally comes with a performance cost on the vanilla environments. We anticipate this benchmark of different DRL methods and the usage of adversarial training to be a starting point for the development of more elaborate navigation strategies that are capable of dealing with uncertain and denied sensor readings.