Experiments in Subsymbolic Action Planning with Mobile Robots
The ability to determine a sequence of actions in order to reach a particular goal is of utmost importance to mobile robots. One major problem with symbolic planning approaches regards assumptions made by the designer while introducing externally specified world models, preconditions and postconditions. To bypass this problem, it would be desirable to develop mechanisms for action planning that are based on the agent’s perceptual and behavioural space, rather than on externally supplied symbolic representations. We present a subsymbolic planning mechanism that uses a non-symbolic representation of sensor-action space, learned through the agent’s autonomous interaction with the environment.
In this paper, we present experiments with two autonomous mobile robots, which use autonomously learned subsymbolic representations of perceptual and behavioural space to determine goal-achieving sequences of actions. The experimental results we present illustrate that such an approach results in an embodied robot planner that produces plans which are grounded in the robot’s perception-action space.
KeywordsMobile Robot Perceptual State Perceptual Space Behavioural Repertoire Action Link
Unable to display preview. Download preview PDF.
- 2.Nilsson, N.J.: Shakey the robot. Technical Report 323, SRI International (1984)Google Scholar
- 4.Arkin, R.: Behavior-Based Robotics. MIT Press, Cambridge (1998)Google Scholar
- 5.Malcolm, C.: Behavioural modules in robotic assembly. Lecture Notes, Division of Informatics, University of Edinburgh (2000)Google Scholar
- 6.Gat, E.: Integrating planning and reacting in a heterogeneous asynchronous architecture for controlling real-world mobile robots. In: Proceedings AAAI 1992, vol. 4, pp. 809–815 (1992)Google Scholar
- 7.Baldassarre, G.: A planning modular neural-network robot for asynchronous multi-goal navigation tasks. In: Proceedings of the 2001 Fourth European Workshop on Advanced Mobile Robots - EUROBOT-2001, pp. 223–230 (2001)Google Scholar
- 8.Baldassarre, G.: Planning with neural networks and reinforcement learning. PhD thesis, University of Essex (2001)Google Scholar
- 9.Turing, A.: The chemical basis for morphogenesis. Phil. Trans. Roy. Soc. 37, 129–152 (1952)Google Scholar
- 10.Steels, L.: Steps towards common sense. In: Proceedings ECAI 1988, pp. 49–54 (1988)Google Scholar
- 13.Zeller, M., Sharma, R., Schulten, K.: Topology representing network for sensor-based robot motion planning. In: Proceedings of the 1996 World Congress on Neural Networks, pp. 100–103. INNS Press (1996)Google Scholar
- 14.Kandel, E.R., Schwartz, J.H., Jessell, T.M. (eds.): Essentials of neural science and behavior. Appleton and Lange, Stanford (1995)Google Scholar