When transferring a learned task to an environment containing new objects, a core problem is identifying the mapping between objects in the old and new environments. This object mapping is dependent on the task being performed and the roles objects play in that task. Prior work assumes (i) the robot has access to multiple new demonstrations of the task or (ii) the primary features for object mapping have been specified. We introduce an approach that is not constrained by either assumption but rather uses structured interaction with a human teacher to infer an object mapping for task transfer. We describe three experiments: an extensive evaluation of assisted object mapping in simulation, an interactive evaluation incorporating demonstration and assistance data from a user study involving 10 participants, and an offline evaluation of the robot's confidence during object mapping. Our results indicate that human-guided object mapping provided a balance between mapping performance and autonomy, resulting in (i) up to 2.25× as many correct object mappings as mapping without human interaction, and (ii) more efficient transfer than requiring the human teacher to re-demonstrate the task in the new environment, correctly inferring the object mapping across 93.3% of the tasks and requiring at most one interactive assist in the typical case.

Human-in-the-loop Machine Learning (HIL-ML) is a widely adopted paradigm for instilling human knowledge in autonomous agents. Many design choices influence the efficiency and effectiveness of such interactive learning processes, particularly the interaction type through which the human teacher may provide feedback. While different interaction types (demonstrations, preferences, etc.) have been proposed and evaluated in the HIL-ML literature, there has been little discussion of how these compare or how they should be selected to best address a particular learning problem. In this survey, we propose an organizing principle for HIL-ML that provides a way to analyze the effects of interaction types on human performance and training data. We also identify open problems in understanding the effects of interaction types.

No abstract

Improvisation is a hallmark of human creativity and serves a functional purpose in completing everyday tasks with novel resources. This is particularly exhibited in tool-using tasks: When the expected tool for a task is unavailable, humans often are able to replace the expected tool with an atypical one. As robots become more commonplace in human society, we will also expect them to become more skilled at using tools in order to accommodate unexpected variations of tool-using tasks. In order for robots to creatively adapt their use of tools to task variations in a manner similar to humans, they must identify tools that fulfill a set of task constraints that are essential to completing the task successfully yet are initially unknown to the robot. In this paper, we present a high-level process for tool improvisation (tool identification, evaluation, and adaptation), highlight the importance of tooltips in considering tool-task pairings, and describe a method of learning by correction in which the robot learns the constraints from feedback from a human teacher. We demonstrate the efficacy of the learning by correction method for both within-task and across-task transfer on a physical robot.

No abstract