Active Perception with Neural Networks
This work tackles the problem of improving robot performance through active perception, but it appears incremental as it highlights recent progress without introducing a new method.
The report addresses the challenge of efficiently coupling perception with action in robotics by leveraging neural networks for semantic interpretation, enabling real-time closing of the perception-action loop.
Active perception has been employed in many domains, particularly in the field of robotics. The idea of active perception is to utilize the input data to predict the next action that can help robots to improve their performance. The main challenge lies in understanding the input data to be coupled with the action, and gathering meaningful information of the environment in an efficient way is necessary and desired. With recent developments of neural networks, interpreting the perceived data has become possible at the semantic level, and real-time interpretation based on deep learning has enabled the efficient closing of the perception-action loop. This report highlights recent progress in employing active perception based on neural networks for single and multi-agent systems.