SINRL: Socially Integrated Navigation with Reinforcement Learning using Spiking Neural Networks
This work addresses energy-efficient and human-like navigation for robots in social settings, representing an incremental advancement by applying neuromorphic methods to DRL.
The paper tackled the problem of integrating autonomous mobile robots into human environments by developing a hybrid socially integrated DRL approach using SNNs and ANNs, resulting in enhanced social navigation performance and an estimated energy consumption reduction of approximately 1.69 orders of magnitude.
Integrating autonomous mobile robots into human environments requires human-like decision-making and energy-efficient, event-based computation. Despite progress, neuromorphic methods are rarely applied to Deep Reinforcement Learning (DRL) navigation approaches due to unstable training. We address this gap with a hybrid socially integrated DRL actor-critic approach that combines Spiking Neural Networks (SNNs) in the actor with Artificial Neural Networks (ANNs) in the critic and a neuromorphic feature extractor to capture temporal crowd dynamics and human-robot interactions. Our approach enhances social navigation performance and reduces estimated energy consumption by approximately 1.69 orders of magnitude.