Sensory Anticipation of Optical Flow in Mobile Robotics
This work addresses collision avoidance for mobile robots, but it appears incremental as it builds on existing methods for optical flow learning and reinforcement learning.
The paper tackled the problem of long-term prediction for collision anticipation in mobile robotics by learning a sensorimotor model online to anticipate optical flow and predict collisions using reinforcement learning, achieving predictions up to a given time horizon.
In order to anticipate dangerous events, like a collision, an agent needs to make long-term predictions. However, those are challenging due to uncertainties in internal and external variables and environment dynamics. A sensorimotor model is acquired online by the mobile robot using a state-of-the-art method that learns the optical flow distribution in images, both in space and time. The learnt model is used to anticipate the optical flow up to a given time horizon and to predict an imminent collision by using reinforcement learning. We demonstrate that multi-modal predictions reduce to simpler distributions once actions are taken into account.