Why Evolve When You Can Adapt? Post-Evolution Adaptation of Genetic Memory for On-the-Fly Control

TL;DR

This paper introduces a real-time adaptation mechanism for robotic controllers that combines genetic algorithms with Hebbian plasticity, allowing robots to dynamically adjust to environmental changes without retraining.

Contribution

The paper presents a novel hybrid GA-Hebbian approach enabling on-the-fly adaptation in robotic controllers through biological-inspired synaptic plasticity, separating learning from memory.

Findings

Effective real-time adaptation during robot navigation tasks

Robustness to environmental changes demonstrated in experiments

Reversion to original weights preserves core knowledge

Abstract

Imagine a robot controller with the ability to adapt like human synapses, dynamically rewiring itself to overcome unforeseen challenges in real time. This paper proposes a novel zero-shot adaptation mechanism for evolutionary robotics, merging a standard Genetic Algorithm (GA) controller with online Hebbian plasticity. Inspired by biological systems, the method separates learning and memory, with the genotype acting as memory and Hebbian updates handling learning. In our approach, the fitness function is leveraged as a live scaling factor for Hebbian learning, enabling the robot's neural controller to adjust synaptic weights on-the-fly without additional training. This adds a dynamic adaptive layer that activates only during runtime to handle unexpected environmental changes. After the task, the robot 'forgets' the temporary adjustments and reverts to the original weights, preserving core knowledge. We validate this hybrid GA-Hebbian controller on an e-puck robot in a T-maze navigation task with changing light conditions and obstacles.