JEDAI: A System for Skill-Aligned Explainable Robot Planning

@inproceedings{Shah2021JEDAIAS,
  title={JEDAI: A System for Skill-Aligned Explainable Robot Planning},
  author={Naman Shah and Pulkit Verma and Trevor Angle and Siddharth Srivastava},
  booktitle={Adaptive Agents and Multi-Agent Systems},
  year={2021}
}
This paper presents JEDAI, an AI system designed for out- reach and educational efforts aimed at non-AI experts. JEDAI features a novel synthesis of research ideas from integrated task and motion planning and explainable AI. JEDAI helps users create high-level, intuitive plans while ensuring that they will be executable by the robot. It also provides users customized explanations about errors and helps improve their understanding of AI planning as well as the limits and capabilities of the… 
[PDF] Semantic Reader

Figures from this paper

References

SHOWING 1-10 OF 40 REFERENCES

Towards providing explanations for robot motion planning

A new taxonomy of kinds and purposes of explanations in this context of motion planning is introduced, focusing not only on explanations of failure but also on contrastive explanations—which explain why a trajectory A was returned by a planner, instead of a different trajectory B expected by the user.

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

An extensive empirical evaluation on twenty different settings using holonomic and non-holonomic robots shows that the learned abstractions provide the information necessary for efficient multi-source hierarchical planning and this approach of learning, abstractions, and planning outperforms state-of-the-art baselines by nearly a factor of ten in terms of planning time on test environments not seen during training.

Using state abstractions to compute personalized contrastive explanations for AI agent behavior

Anytime Integrated Task and Motion Policies for Stochastic Environments

It is proved that the algorithm is probabilistically complete and can compute feasible solution policies in an anytime fashion so that the probability of encountering an unresolved contingency decreases over time.

Evaluating CoBlox: A Comparative Study of Robotics Programming Environments for Adult Novices

A block-based interface for programming a one-armed industrial robot is created and a study with 67 adult novices comparing it to two programming approaches in widespread use in industry shows it successfully implemented robot programs faster with no loss in accuracy while reporting higher scores for usability, learnability, and overall satisfaction.

Anytime Stochastic Task and Motion Policies

It is proved that the algorithm is probabilistically complete and can compute feasible solution policies in an anytime fashion so that the probability of encountering an unresolved contingency decreases over time.

OpenRAVE: A Planning Architecture for Autonomous Robotics

This work introduces an open-source cross-platform software architecture called OpenRAVE, the Open Robotics and Animation Virtual Environment, targeted for real-world autonomous robot applications, and includes a seamless integration of 3-D simulation, visualization, planning, scripting and control.

A Graphical Model-Based Representation for Classical AI Plans using Category Theory

The approach of this paper is to view the actions as maps between literals and the selected plan as a composition of those maps, and to propose an algorithm agnostic, model-based representation for domains, problems, and plans expressed in the commonly used planning description language, PDDL.

RADAR-X: An Interactive Interface Pairing Contrastive Explanations with Revised Plan Suggestions

This work empower existing decision support technologies to engage in an interactive explanatory dialogue with the user and provide contrastive explanations based on user-specified foils to reach a consensus on proposed decisions.

RADAR-X: An Interactive Mixed Initiative Planning Interface Pairing Contrastive Explanations and Revised Plan Suggestions

This work presents RADAR-X, a decision support system that showcases the ability to engage the user in an interactive explanatory dialogue by first enabling them to specify an alternative to a proposed decision, and then providing contrastive explanations to these user-specified foils which helps the user understand why a specific plan was chosen over the alternative.