Generating robot action plans by means of an heuristic search

Frommherz, Bernhard J.; Werling, Gerhard

doi:10.1109/robot.1990.126101

Cited by 10 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example Farritor and Dubowsky build a climbing robot which uses planning to find a sequence of actions which achieves its goal [10]. In earlier work Frommherz and Werling propose using heuristic search for planning and show experiments in a simple assembly task [11]. Compared to the problem considered in this paper, in the mentioned papers the action effects are not nearly as uncertain.…”

Section: Related Workmentioning

confidence: 96%

Instance-Based Action Models for Fast Action Planning

Ahmadi

Stone

2008

RoboCup 2007: Robot Soccer World Cup XI

View full text Add to dashboard Cite

Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is learned empirically by robots trying actions in the environment. Modeling the action planning problem as a Markov decision process, the action model is used to build the transition function. In static environments, standard value iteration techniques are used for computing the optimal policy. In dynamic environments, an algorithm is proposed for fast replanning, which updates a subset of state-action values computed for the static environment. As a test-bed, the goal scoring task in the RoboCup 4-legged scenario is used. The algorithms are validated in the problem of planning kicks for scoring goals in the presence of opponent robots. The experimental results both in simulation and on real robots show that the instance-based action model boosts performance over using parametric models as done previously, and also incremental replanning significantly improves over original off-line planning.

show abstract

Section: Related Workmentioning

confidence: 96%