Learning to reach after learning to look: A study of autonomy in learning sensorimotor transformations

Abstract

Abstract-This paper presents a neurally-inspired architecture for learning to reach toward visually-perceived targets. The whole behavioural loop from object perception to motor control is realised in the architecture of interconnected Dynamic Neural Fields. The sensory-motor mappings, involved in generation of saccadic gaze shifts and reaching arm movements, adapt in the system autonomously along with the generated behaviour. A network of neural-dynamic nodes organises activation and deactivation of the behavioural modules of the architecture in time, leading to an autonomous process model of development of looking and reaching. The architecture was implemented and validated in a simulated robotic agent.

Pose Estimation and Map Formation with Spiking Neural Networks: towards Neuromorphic SLAM

“…Finally, both detection of the loop-closure events and use of the estimated errors to calibrate the path integration and correct the map require development of new spiking neural network architectures that enable "autonomous", online learning and adaptation. We have made first steps toward such architectures using continuous a ractor dynamics [38], [39], [31]; their realization in neuromorphic hardware is yet an outstanding goal.…”