- A critical challenge in robot learning from demonstration is the ability to map the behavior of the trainer onto a robot’s existing repertoire of basic/primitive capabilities. The robot must process a continuous stream of data coming from its sensors and cast this information onto its knowledge and control repertoire. In most cases, this consists of segmenting the data stream into meaningful units, and then mapping them into appropriate skills or tasks. The difficulty of the policy transfer problem is increased due to a current divide between the complexity of robot control architectures and their ability to support automatic construction of controllers through learning. In part, this problem is due to the fact that the observed behavior of the teacher may consist of a combination (or superposition) of the robot’s individual primitives. The problem becomes more complex when the task involves temporal sequences of goals.
- We developed an autonomous control architecture that allows for learning of hierarchical task representations, in which: 1) every goal is achieved through a linear superposition (or fusion) of robot primitives and 2) sequencing across goals is achieved through arbitration. We treat learning of the appropriate superposition as a state estimation problem over the space of possible linear fusion weights, inferred through a particle filter. The contributions of the proposed control architecture are that it enables: 1) the use of both command arbitration and fusion within a single control representation and 2) automated construction of such representations from demonstration. Historically, these two main action selection mechanisms have been mostly employed separately in robot control, thus limiting the range of tasks that robots can execute. By recognizing the ability of arbitration to encode temporal sequences and the ability of fusion to combine concurrently running behaviors, we merge the strengths and features of both within a unique task representation.
- Liesl Wigand, Monica Nicolescu, Mircea Nicolescu, "A Developmental Approach to Concept Learning", Proceedings of the International Conference on Informatics in Control, Automation and Robotics, pages 337-344, Reykjavik, Iceland, July 2013. [PDF] [Link]
- Monica Nicolescu, Odest Chadwicke Jenkins, Adam Olenderski, Eric Fritzinger, "Learning Behavior Fusion from Observation", Interactive Studies Journal, Special Issue on Robot and Human Interactive Communication , vol. 9, no. 2, pages 319-352, 2008. [PDF]
- Monica Nicolescu, Odest Chadwicke Jenkins, Austin Stanhope, "Fusing Robot Behaviors for Human-Level Tasks", in Proceedings, IEEE International Conference on Development and Learning (ICDL 07), London, UK, July 11-13, 2007. [PDF]
- Monica Nicolescu, Odest Chadwicke Jenkins, Adam Olenderski, "Learning Behavior Fusion Estimation from Demonstration", in Proceedings, IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 06), Hatfield, UK, pages 340-345, September 6-8, 2006. [Link]
- Monica Nicolescu, Odest Chadwicke Jenkins, Adam Olenderski, "Behavior Fusion Estimation for Robot Learning from Demonstration", in Proceedings, IEEE 2006 Workshop on Distributed Intelligent Systems (DIS06), Prague, Czech Republic, pages 31-36, June 15-16, 2006. [PDF]
Learning a left wall following behavior
Learning a circling behavior
Learning a sequence of fused behaviors
Learning a composition of fused behaviors
- Design and Evaluation of Methods for Robot Learning by Demonstration, National Science Foundation, Early Career Development Award (CAREER), PI, Amount: $410,000, January 15, 2006 - January 14, 2011.