Learning symbolic representations of actions from human demonstrations

Abstract

Abstract-In this paper, a robot learning approach is proposed which integrates Visuospatial Skill Learning, Imitation Learning, and conventional planning methods. In our approach, the sensorimotor skills (i.e., actions) are learned through a learning from demonstration strategy. The sequence of performed actions is learned through demonstrations using Visuospatial Skill Learning. A standard action-level planner is used to represent a symbolic description of the skill, which allows the system to represent the skill in a discrete, symbolic form. The Visuospatial Skill Learning module identifies the underlying constraints of the task and extracts symbolic predicates (i.e., action preconditions and effects), thereby updating the planner representation while the skills are being learned. Therefore the planner maintains a generalized representation of each skill as a reusable action, which can be planned and performed independently during the learning phase. Preliminary experimental results on the iCub robot are presented.

Evaluating Methods for End-User Creation of Robot Task Plans

“…These developments have led to a growing interest in making it easy for domain experts to transfer knowledge to collaborative robots, either through a user interface [2], [3], [4], [5], natural language [6], or learning from demonstration [7], [8], [9], [10]. To take full advantage of these systems, the human user must have an accurate mental model of a robot's capabilities [11].…”

“…Recent approaches for end-user instruction of collaborative robots include the development of new user interfaces [2], [3], [4], learning from demonstration [7], [10], or systems that make use of natural language together with ontologies and large knowledge bases to follow high-level instructions, such as Tell Me Dave [6] or RoboSherlock [12].…”

“…An alternate approach to direct task specification is to learn tasks from expert demonstrations. Alizadeh et al [7] learn skills which can be re-used according to a PDDL planner. Levine et al [8] proposed reinforcement learning methods for effectively learning individual skills with a demonstration as a prior.…”

Evaluation of a robot programming framework for non-experts using symbolic planning representations

“…Moreover, the robot often tries to learn the teacher's goal [4], [12] and reproduces it from different initial states. Once the goal changes, the teacher needs to demonstrate a new action sequence.…”

“…To learn high-level conditions, the robot uses a perception system (e.g. SIFT [12] or a database of object features [15]) that recognises object properties in the state of the world. In our experiments, we implemented a simple python algorithm with integrated functionalities of the Robot Operating System (ROS), to detect and move objects, based on their colour.…”