Reinforcement learning for robots using neural networks
Reinforcement learning for robots using neural networks
Swarm intelligence: from natural to artificial systems
Swarm intelligence: from natural to artificial systems
Robot Motion Planning
Self-Organization in Biological Systems
Self-Organization in Biological Systems
Forward chaining for robot and agent navigation using potential fields
ACSC '04 Proceedings of the 27th Australasian conference on Computer science - Volume 26
Modeling adaptive autonomous agents
Artificial Life
Editorial: Towards Autonomous Robotic Systems - Mobile Robotics in the UK
Robotics and Autonomous Systems
Reactive planning for olfactory-based mobile robots
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Hi-index | 0.00 |
We propose a new, extended artificial potential field method, which uses dynamic internal agent states. The internal states are modeled as a dynamical system of coupled first order differential equations that manipulate the potential field in which the agent is situated. The internal state dynamics are forced by the interaction of the agent with the external environment. Local equilibria in the potential field are then manipulated by the internal states and transformed from stable equilibria to unstable equilibria, allowing escape from local minima in the potential field. This new methodology successfully solves reactive path planning problems, such as a complex maze with multiple local minima, which cannot be solved using conventional static potential fields.