Kognitive Robotik — Herausforderungen an unser Verständnis natürlicher Umgebungen

Zusammenfassung Wir diskutieren einen Ansatz, der kognitive Robotik als die Erweiterung der Methoden der Robotik — insb. Lernen, Planen und Regelung — auf „äußere Freiheitsgrade“ versteht. Damit verschiebt sich der Fokus: Weg von Gelenkwinkeln, Vektorräumen und Gauß'schen Verteilungen, hin zu den Objekten und der Struktur der Umwelt. Letztere können wir nur schwer formalisieren und in geeignete Repräsentationen und Priors übersetzen, mit denen effizientes Lernen und Planen möglich wird. Es wird deutlich, welche theoretischen Probleme sich hinter dem Ziel automomer Systeme verbergen, die durch intelligente Exploration und Verallgemeinerung ihre Umwelt zu verstehen lernen und die gelernten Modelle zur Handlungsplanung nutzen. Die momentan diskutierte Integration von Logik, Geometrie und Wahrscheinlichkeiten — und damit die Überbrückung der klassischen Disziplinbarrieren zwischen Robotik, Künstlicher Intelligenz und statistischer Lerntheorie — ist eine der zwangsläufigen Herausforderungen der kognitiven Robotik. In diesem Kontext skizzieren wir eigene Beiträge zum relationalen Reinforcement-Lernen, zur Exploration und dem Symbol-Lernen. Abstract We discuss that “cognitive robotics” implies the extension of classical robotics methods — esp. planning, control and learning — to external degrees of freedom (DoFs). External refers to the articulated and manipulable DoFs of the environment and the objects therein. Coping with these DoFs requires to go beyond vector spaces and Gaussian distributions and instead address the complex structure of natural environments, which is hard to formalize and translate to appropriate representations and priors for efficient learning. With this discussion we aim to highlight the theoretical challenges behind the goal of robots that autonomously explore their environment and learn to manipulated external DoFs. The integration of logic, geometry and probabilities is one of these challenges. In this context we briefly sketch own work on relational reinforcement learning, exploration and symbol learning.

[1]  P. Dayan,et al.  Opinion TRENDS in Cognitive Sciences Vol.10 No.8 Full text provided by www.sciencedirect.com A normative perspective on motivation , 2022 .

[2]  Nico Blodow,et al.  The Assistive Kitchen — A demonstration scenario for cognitive technical systems , 2007, RO-MAN 2008 - The 17th IEEE International Symposium on Robot and Human Interactive Communication.

[3]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[4]  Sebastian Thrun,et al.  Towards programming tools for robots that integrate probabilistic computation and learning , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[5]  L. P. Kaelbling,et al.  Learning Symbolic Models of Stochastic Domains , 2007, J. Artif. Intell. Res..

[6]  Stefanie Tellex,et al.  Toward understanding natural language directions , 2010, 2010 5th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[7]  Marc Toussaint,et al.  Planning with Noisy Probabilistic Relational Rules , 2010, J. Artif. Intell. Res..

[8]  Luc Steels,et al.  Flexible word meaning in embodied agents , 2008, Connect. Sci..

[9]  Marc Toussaint,et al.  Exploration in relational domains for model-based reinforcement learning , 2012, J. Mach. Learn. Res..

[10]  Tamim Asfour,et al.  ARMAR-III: An Integrated Humanoid Platform for Sensory-Motor Control , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[11]  Marc Toussaint,et al.  Learning Grounded Relational Symbols from Continuous Data for Abstract Reasoning , 2013 .

[12]  J. Feldman Symbolic representation of probabilistic worlds , 2012, Cognition.

[13]  Ronen I. Brafman,et al.  R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning , 2001, J. Mach. Learn. Res..

[14]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[15]  Nils J. Nilsson,et al.  Shakey the Robot , 1984 .

[16]  Leslie Pack Kaelbling,et al.  Hierarchical task and motion planning in the now , 2011, 2011 IEEE International Conference on Robotics and Automation.

[17]  Jesse Hoey,et al.  An analytic solution to discrete Bayesian reinforcement learning , 2006, ICML.

[18]  David Andre,et al.  Programmable Reinforcement Learning Agents , 2000, NIPS.

[19]  Stefan Schaal,et al.  Incremental Online Learning in High Dimensions , 2005, Neural Computation.

[20]  Helge J. Ritter,et al.  Situated robot learning for multi-modal instruction and imitation of grasping , 2004, Robotics Auton. Syst..