Open AccessProceedings Article
Collaborative Planning with Encoding of Users' High-Level Strategies.
Joseph Kim,Christopher J. Banks,Julie A. Shah +2 more
- pp 955-962
Reads0
Chats0
TLDR
This work explores a framework in which users provide high-level strategies encoded as soft preferences to guide the low-level search of the planner, and shows that the resulting plans achieve greater similarity to those generated by humans with regard to the produced sequences of actions.Abstract:
The generation of near-optimal plans for multi-agent systems with numerical states and temporal actions is computationally challenging. Current off-the-shelf planners can take a very long time before generating a near-optimal solution. In an effort to reduce plan computation time, increase the quality of the resulting plans, and make them more interpretable by humans, we explore collaborative planning techniques that actively involve human users in plan generation. Specifically, we explore a framework in which users provide high-level strategies encoded as soft preferences to guide the low-level search of the planner. Through human subject experimentation, we empirically demonstrate that this approach results in statistically significant improvements to plan quality, without substantially increasing computation time. We also show that the resulting plans achieve greater similarity to those generated by humans with regard to the produced sequences of actions, as compared to plans that do not incorporate userprovided strategies.read more
Citations
More filters
Proceedings Article
Bayesian Inference of Temporal Task Specifications from Demonstrations
TL;DR: This work presents Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula that incorporates methods from probabilism programming to define the authors' priors, along with a domain-independent likelihood function to enable sampling-based inference.
Proceedings ArticleDOI
Bayesian Inference of Linear Temporal Logic Specifications for Contrastive Explanations
TL;DR: This paper presents BayesLTL – a Bayesian probabilistic model for inferring contrastive explanations as linear temporal logic (LTL) specifications, and demonstrates the robustness and scalability of the model for inference accurate specifications from noisy data and across various benchmark planning domains.
Proceedings Article
RADAR - A Proactive Decision Support System for Human-in-the-Loop Planning.
Sailik Sengupta,Tathagata Chakraborti,Sarath Sreedharan,Satya Gautam Vadlamudi,Subbarao Kambhampati +4 more
TL;DR: This paper considers the case of HILP where the human responsible for making the decisions in complex scenarios are supported by an automated planning system and proposes a PDS framework RADAR based on research in the automated planning community that aids the human decision maker in constructing plans.
Journal ArticleDOI
Prediction of intention during interaction with iCub with Probabilistic Movement Primitives
Oriane Dermy,Oriane Dermy,Oriane Dermy,Alexandros Paraschos,Alexandros Paraschos,Marco Ewerton,Jan Peters,Jan Peters,François Charpillet,François Charpillet,François Charpillet,Serena Ivaldi,Serena Ivaldi,Serena Ivaldi +13 more
TL;DR: An approach to endow the iCub with basic capabilities of intention recognition, based on Probabilistic Movement Primitives (ProMPs), a versatile method for representing, generalizing, and reproducing complex motor skills is proposed.
Book ChapterDOI
Multi-Modal Intention Prediction With Probabilistic Movement Primitives
TL;DR: It is shown that if the partner guides the robot with the gaze cue, the robot recognizes the intended action primitive even in the case of ambiguous actions, which greatly improves the prediction of the future intended trajectory during a physical interaction.
References
More filters
Journal ArticleDOI
PDDL2.1: an extension to PDDL for expressing temporal planning domains
Maria Fox,Derek Long +1 more
TL;DR: PDDL2.1 as discussed by the authors is a modelling language capable of expressing temporal and numeric properties of planning domains and has been used in the International Planning Competitions (IPC) since 1998.
Proceedings ArticleDOI
Enhancing the explanatory power of usability heuristics
TL;DR: A new set of nine heuristics were derived: visibility of system status, match between system and the real world, user control and freedom, consistency and standards, error prevention, recognition rather than recall, flexibility and efficiency of use, aesthetic and minimalist design, and helping users recognize, diagnose, and recover from errors.
Journal ArticleDOI
SHOP2: an HTN planning system
TL;DR: The SHOP2 planning system as discussed by the authors received one of the awards for distinguished performance in the 2002 International Planning Competition and described the features that enabled it to excel in the competition, especially those aspects of SHOP 2 that deal with temporal and metric planning domains.
Proceedings Article
TRIPs: an integrated intelligent problem-solving assistant
George Ferguson,James F. Allen +1 more
TL;DR: How the integrated system provides key advantages for helping both work in natural language dialogue processing and in interactive planning and problem solving is discussed, and the opportunities such an approach affords for the future are considered.
Proceedings Article
TRAINS-95: towards a mixed-initiative planning assistant
TL;DR: The implementation of a prototype version of a mixed-initiative planning system, TRAINS-95, which helps a manager solve routing problems in a simple transportation domain, and how traditional planning technology does not play a major role in the system is described.