EPOC: Efficient Perception via Optimal Communication


  • Masoumeh Heidari Kapourchali University of Memphis
  • Bonny Banerjee University of Memphis




We propose an agent model capable of actively and selectively communicating with other agents to predict its environmental state efficiently. Selecting whom to communicate with is a challenge when the internal model of other agents is unobservable. Our agent learns a communication policy as a mapping from its belief state to with whom to communicate in an online and unsupervised manner, without any reinforcement. Human activity recognition from multimodal, multisource and heterogeneous sensor data is used as a testbed to evaluate the proposed model where each sensor is assumed to be monitored by an agent. The recognition accuracy on benchmark datasets is comparable to the state-of-the-art even though our model uses significantly fewer parameters and infers the state in a localized manner. The learned policy reduces number of communications. The agent is tolerant to communication failures and can recognize unreliable agents through their communication messages. To the best of our knowledge, this is the first work on learning communication policies by an agent for predicting its environmental state.




How to Cite

Heidari Kapourchali, M., & Banerjee, B. (2020). EPOC: Efficient Perception via Optimal Communication. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4107-4114. https://doi.org/10.1609/aaai.v34i04.5830



AAAI Technical Track: Machine Learning