Toward Open Knowledge Enabling for Human- Robot Interaction

Abstract

This paper presents an effort to enable robots to utilize open-source knowledge resources autonomously for human-robot interaction. The main challenges include how to extract knowledge in semi-structured and unstructured natural languages, how to make use of multiple types of knowledge in decision making, and how to identify the knowledge that is missing. A set of techniques for multi-mode natural language processing, integrated decision making, and open knowledge searching is proposed. The OK-KeJia robot prototype is implemented and evaluated, with special attention to two tests on 11,615 user tasks and 467 user desires. The experiments show that the overall performance improves remarkably due to the use of appropriate open knowledge.

Towards an Explanation Generation System for Robots: Analysis and Recommendations

“…The KnowRob architecture for service robots uses knowledge bases created from different sources to perform limited analysis of the reasons for unexpected observations [27]. Other examples include the use of ASP for planning and diagnostics by one or more simulated robot housekeepers [28] and mobile robot teams [29] and by robots reasoning about domain knowledge learned through natural language interactions with humans [30]. More recent architectures that support logic-based reasoning and probabilistic reasoning with common sense knowledge, also include the ability to generate explanations.…”

From Structured Task Instructions to Robot Task Plans

“…Our previous work Chen et al, 2012) also provided an approach on converting semi-structured natural language instructions to structured representations. Here we focus on how to represent both functional and procedural knowledge of structured task instructions.…”

“…A task planning system based on causal theories has been implemented on our service robot (Chen et al, 2010;Chen et al, 2012). A logic programming language named Answer Set Programming (ASP) (Baral, 2003) is chosen for the calculation of causal theories and an efficient ASP solver iclingo (Gebser et al, 2008) is used for computing task plans.…”

BWIBots: A platform for bridging the gap between AI and human–robot interaction research

“…The Kejia robot, winner of Robocup@Home in 2014 (Chen et al 2014), has been used to identify what knowledge is necessary to completely ground human requests, and search for missing information using open knowledge, i.e. free-form knowledge available online (Chen, Xie, Ji and Sui 2012). While the RoboCup@Home competition is designed to test the versatility of service robots, and benchmarks test a breadth of capabilities, research contributions performed using the BWIBots are more focused and improve the state-of-the-art on somewhat more specialized, but deeper, problems than those typically defined by RoboCup@Home.…”