VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation
This addresses the challenge of enabling imitation learning for robots when demonstration data is hard to collect due to platform constraints, offering a practical solution for autonomous navigation.
The paper tackles the problem of imitation learning for vision-based autonomous navigation without requiring state-action demonstrations from the deployment platform, by introducing VOILA, which learns navigation policies from a single video demonstration collected from a physically different agent. The result shows that VOILA successfully imitates the expert in simulation and generalizes to novel environments, with real-world validation on a wheeled robot using a mobile phone video.
While imitation learning for vision based autonomous mobile robot navigation has recently received a great deal of attention in the research community, existing approaches typically require state action demonstrations that were gathered using the deployment platform. However, what if one cannot easily outfit their platform to record these demonstration signals or worse yet the demonstrator does not have access to the platform at all? Is imitation learning for vision based autonomous navigation even possible in such scenarios? In this work, we hypothesize that the answer is yes and that recent ideas from the Imitation from Observation (IfO) literature can be brought to bear such that a robot can learn to navigate using only ego centric video collected by a demonstrator, even in the presence of viewpoint mismatch. To this end, we introduce a new algorithm, Visual Observation only Imitation Learning for Autonomous navigation (VOILA), that can successfully learn navigation policies from a single video demonstration collected from a physically different agent. We evaluate VOILA in the photorealistic AirSim simulator and show that VOILA not only successfully imitates the expert, but that it also learns navigation policies that can generalize to novel environments. Further, we demonstrate the effectiveness of VOILA in a real world setting by showing that it allows a wheeled Jackal robot to successfully imitate a human walking in an environment using a video recorded using a mobile phone camera.