Biologically inspired spiking neural networks for energy-efficient robot learning and control

Energy-efficient learning and control are becoming increasingly crucial for robots that solve complex real-world tasks with limited onboard resources. Although deep neural networks (DNN) have been successfully applied to robotics, their high energy consumption limits their use in low-power edge applications. Biologically inspired spiking neural networks (SNN), facilitated by the advances in neuromorphic processors, have started to deliver energy-efficient, massively parallel, and low-latency solutions to robotics. This dissertation presents our energy-efficient neuromorphic solutions to robot navigation, control, and learning, using SNNs on the neuromorphic processor. First, we propose a biologically constrained SNN, mimicking the brain's spatial system, solving the unidimensional SLAM problem while only consuming 1% of energy compared with the conventional filter-based approach. In addition, when extending the model to 2D environments by adding biologically realistic hippocampal neurons, the SNN formed cognitive maps in real-time and helped study the neuronal interconnectivity and cognitive functions. Next, the dissertation shows how the neuromorphic approach can be extended to high-level cognitive functions such as learning control policies. Specifically, we propose a reinforcement co-learning framework that jointly trains a spiking actor network (SAN) with a deep critic network using backpropagation to learn optimal policies for both mapless navigation and high-dimensional continuous control. Compared with state-of-the-art DNN approaches, our method results in up to 140 times less energy consumption during inference, while generating a superior successful rate on mapless navigation, and achieves the same level of performance on high-dimensional continuous control when using the population-coded spiking actor network (PopSAN). Lastly, we explore how these energy gains can further be extended to training through the development of a biologically plausible gradient-based learning framework on the neuromorphic processor. The learning method is functionally equivalent to the spatiotemporal backpropagation but solely relies on spike-based communication, local information processing, and rapid online computation, which are the main neuromorphic principles that mimic the brain. Overall, work in this dissertation pushes the frontiers of SNN applications to energy-efficient robotic control and learning, and hence paves the way toward the introduction of a biologically inspired alternative solution for autonomous robots running on energy-efficient neuromorphic processors.Ph.D.Includes bibliographical reference