Teaching Commonsense and Dynamic Knowledge to Service Robots

Opfer, Stephan; Jakob, Stefan; Geihs, Kurt

doi:10.1007/978-3-030-35888-4_60

Cited by 5 publications

(20 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KnowRob has multiple knowledge representation and reasoning capabilities and has been successfully deployed in complex tasks, such as identifying missing items on a table [38], operating containers [39], multi-robot coordination [40], and semantic mapping [41]. Non-monotonic knowledge representation and reasoning systems are typically based on Answer Set Programming (ASP) (e.g., References [29,42,43]) and extensions of OWL-DL that allow the use of incomplete information have been defined (e.g., References [44]), some of which have been demonstrated in different complex tasks [42,[44][45][46][47][48]. Awaad et al [44] use OWL-DL to model preferences and functional affordances for establishing social-accepted behaviors and guidelines to improve human-robot interaction and carrying out tasks in real-world scenarios.…”

Section: Related Workmentioning

confidence: 99%

Deliberative and Conceptual Inference in Service Robots

et al. 2021

View full text Add to dashboard Cite

Service robots need to reason to support people in daily life situations. Reasoning is an expensive resource that should be used on demand whenever the expectations of the robot do not match the situation of the world and the execution of the task is broken down; in such scenarios, the robot must perform the common sense daily life inference cycle consisting on diagnosing what happened, deciding what to do about it, and inducing and executing a plan, recurring in such behavior until the service task can be resumed. Here, we examine two strategies to implement this cycle: (1) a pipe-line strategy involving abduction, decision-making, and planning, which we call deliberative inference and (2) the use of the knowledge and preferences stored in the robot’s knowledge-base, which we call conceptual inference. The former involves an explicit definition of a problem-space that is explored through heuristic search, and the latter is based on conceptual knowledge, including the human user preferences, and its representation requires a non-monotonic knowledge-based system. We compare the strengths and limitations of both approaches. We also describe a service robot conceptual model and architecture capable of supporting the daily life inference cycle during the execution of a robotics service task. The model is centered in the declarative specification and interpretation of robot’s communication and task structure. We also show the implementation of this framework in the fully autonomous robot Golem-III. The framework is illustrated with two demonstration scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Deliberative and Conceptual Inference in Service Robots

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A number of projects showed that ASP meets the requirements for semantic specifications in a wide range of application areas in terms of expressiveness, efficiency, dynamic extensibility, and scalability. Examples are semantic service adaptation [68], dynamic information stream configuration in crisis management scenarios [57], and service robotics [59]. Thus, by adding semantic annotations to team plans, the developer lays the foundation for re-planning at runtime based on the specified properties and constraints for the robots and their relationships.…”

Section: Robustness and Dynamic Adaptationmentioning

confidence: 99%

“…While there is a large set of publications focusing on knowledge representation techniques for robotic applications (e.g., [58][59][60]), little was published specifically on distributed knowledge bases for multi-robot systems. One thread of research-in particular for service robots-looked at offloading the knowledge base to the cloud [61].…”

mentioning

confidence: 99%

Engineering Challenges Ahead for Robot Teamwork in Dynamic Environments

Geihs

2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The increasing number of robots around us creates a demand for connecting these robots in order to achieve goal-driven teamwork in heterogeneous multi-robot systems. In this paper, we focus on robot teamwork specifically in dynamic environments. While the conceptual modeling of multi-agent teamwork was studied extensively during the last two decades and commercial multi-agent applications were built based on the theoretical foundations, the steadily increasing use of autonomous robots in many application domains gave the topic new significance and shifted the focus more toward engineering concerns for multi-robot systems. From a distributed systems perspective, we discuss general engineering challenges that apply to robot teamwork in dynamic application domains and review state-of-the-art solution approaches for these challenges. This leads us to open research questions that need to be tackled in future work.

show abstract

“…The approach presented by Erdem et al is similar to the integration of commonsense knowledge into the knowledge base of a robot shown by us in [104,107]. Besides using ConceptNet 5 instead of ConceptNet 4, the extracted knowledge is directly translated into ASP instead of using Prolog.…”

Section: Application Of Commonsense Knowledgementioning

confidence: 99%

“…Erdem et al only use the AtLocation and HasProperty relation to prevent possible inconsistencies. In contrast, the full set of over 34 base relations is applied in [104,107]. To prevent semantic inconsistencies in the knowledge base of a robot, we introduce an automatic prevention of inconsistencies in [78], which relies on commonsense knowledge to find contradictions in the properties of an object.…”

Section: Application Of Commonsense Knowledgementioning

confidence: 99%

A Self-Organising Multi-Agent Knowledge Base

Jakob

Jahl

Baraki

et al. 2020

2020 IEEE International Conference on Web Services (ICWS)

Self Cite

View full text Add to dashboard Cite

1 bird(tweety). 2 bird(tux). 3 penguin(tux). 4 flies(X) :-bird(X), not -flies(X). 5 -flies(X) :-bird(X), penguin(X). 6 :-flies(X), -flies(X). Listing 2.1: Example ASP ProgramAdditionally, ASP supports formulating disjunctions in the rule heads. An example of a disjunctive rule is given in Line 3 in Listing 2.2. This rule states that a bird can either fly or not fly.1 bird(tweety). 2 bird(tux). 3 -flies(X), flies(X) :-bird(X). Listing 2.2: Disjunctive ASP Program1 bird(tweety). 2 bird(tux). 3 penguin(tux). 4 flies(tweety) :-bird(tweety), not -flies(tweety). 5 flies(tux) :-bird(tux), not -flies(tux). 6 -flies(tux) :-bird(tux), penguin(tux). 7 :-flies(tweety), -flies(tweety). 8 :-flies(tux), -flies(tux).

show abstract

Teaching Commonsense and Dynamic Knowledge to Service Robots

Cited by 5 publications

References 11 publications

Deliberative and Conceptual Inference in Service Robots

Deliberative and Conceptual Inference in Service Robots

Engineering Challenges Ahead for Robot Teamwork in Dynamic Environments

A Self-Organising Multi-Agent Knowledge Base

Contact Info

Product

Resources

About