This paper reports on experiments involving a hexapod robot. Motivated by neurobiological evidence that control in real hexapod insects is distributed leg-wise, we investigated two approaches to learning distributed controllers: genetic algorithms and reinforcement learning. In the case of reinforcement learning, a new learning algorithm was developed to encourage cooperation between legs. Results from both approaches are presented and compared.
Autonomous robotic excavation has often been limited to a single robotic platform using a specified excavation vehicle. This paper presents a novel method for developing scalable controllers for use in multirobot scenarios and that do not require human defined operations scripts nor extensive modeling of the kinematics and dynamics of the excavation vehicles. Furthermore, the control system does not require specifying an excavation vehicle type such as a bulldozer, frontloader or bucket-wheel and it can evolve to select for an appropriate choice of excavation vehicles to successfully complete a task. The "Artificial Neural Tissue" (ANT) architecture is used as a control system for autonomous multirobot excavation and clearing tasks. This control architecture combines a variable-topology neural-network structure with a coarsecoding strategy that permits specialized areas to develop in the tissue. Training is done in a low-fidelity grid world simulation environment and where a single global fitness function and a set of allowable basis behaviors need be specified. This approach is found to provide improved training performance over fixedtopology neural networks and can be easily ported onto different robot platforms. Aspects of the controller functionality have been tested using high fidelity dynamics simulation and in hardware. An evolutionary training process discovers novel decentralized methods of cooperation employing aggregation behaviors (via synchronized movements). These aggregation behaviors are found to improve controller scalability (with increasing robot density) and better handle robot interference (antagonism) that reduces the overall efficiency of the group.
Abstract.A simple evolutionary approach to developing walking gaits for a legged robot is presented. Each leg of the robot is given its own controller in the form of a cellular automaton which serves to arbitrate between a number of fixed basis behaviours. Local communication exists between neighbouring legs. Genetic algorithms search for cellular automata whose arbitration results in successful walking gaits. An example simulation of the technique is presented as well as results of application to Kafka, a hexapod robot.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.