Pulsed Neural Networks
Hi-index | 0.00 |
The rapid control of sonar-guided vehicles through obstacle fields has been a goal of robotics for decades. How sensory data are represented strongly affects how obstacles and goal information can be combined to select a direction of travel. Many approaches combine attractive and repulsive effects to steer; we have implemented an algorithm that first evaluates the desirability of different directions followed by a winner-take-all (WTA) mechanism to guide steering. We describe a neuromorphic VLSI implementation of this algorithm using the inherent echo delay of obstacles to produce a range-dependent gain in a "race-to-first-spike" neural WTA circuit.