TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Mitrevski, Alex
A1  - Plöger, Paul G.
A1  - Lakemeyer, Gerhard
T1  - Representation and Experience-Based Learning of Explainable Models for Robot Action Execution
T2  - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 25-29, 2020, Las Vegas, NV, USA (Virtual)
N2  - For robots acting in human-centered environments, the ability to improve based on experience is essential for reliable and adaptive operation; however, particularly in the context of robot failure analysis, experience-based improvement is only useful if robots are also able to reason about and explain the decisions they make during execution. In this paper, we describe and analyse a representation of execution-specific knowledge that combines (i) a relational model in the form of qualitative attributes that describe the conditions under which actions can be executed successfully and (ii) a continuous model in the form of a Gaussian process that can be used for generating parameters for action execution, but also for evaluating the expected execution success given a particular action parameterisation. The proposed representation is based on prior, modelled knowledge about actions and is combined with a learning process that is supervised by a teacher. We analyse the benefits of this representation in the context of two actions – grasping handles and pulling an object on a table – such that the experiments demonstrate that the joint relational-continuous model allows a robot to improve its execution based on experience, while reducing the severity of failures experienced during execution.
KW  - Robot learning
KW  - Explainable robotics
KW  - Cognitive robot control
SN  - 978-1-7281-6212-6
SB  - 978-1-7281-6212-6
U6  - https://doi.org/10.1109/IROS45743.2020.9341470
DO  - https://doi.org/10.1109/IROS45743.2020.9341470
N1  - Abstract provided by the author.
SP  - 5641
EP  - 5647
PB  - IEEE
ER  -