Integration of Planning with Recognition for Responsive Interaction Using Classical Planners

@inproceedings{Freedman2017IntegrationOP,
  title={Integration of Planning with Recognition for Responsive Interaction Using Classical Planners},
  author={Richard Gabriel Freedman and Shlomo Zilberstein},
  booktitle={AAAI},
  year={2017}
}
Interaction between multiple agents requires some form of coordination and a level of mutual awareness. When computers and robots interact with people, they need to recognize human plans and react appropriately. Plan and goal recognition techniques have focused on identifying an agent's task given a sufficiently long action sequence. However, by the time the plan and/or goal are recognized, it may be too late for computing an interactive response. We propose an integration of planning with… 

Figures from this paper

Active Goal Recognition
TLDR
This work proposes to combine goal recognition with other observer tasks in order to obtain active goal recognition (AGR), and provides a model and preliminary experimental results for one form of this composite problem.
Responsive Planning and Recognition for Closed-Loop Interaction
TLDR
This work introduces a closed-loop interactive agent framework that integrates planning and recognition to predict what the user is trying to accomplish and autonomously decide on actions to take in response to these predictions.
Solving navigation-based goal recognition design problems with action graphs
TLDR
Experiments show that the proposed approach is able to force humans into revealing their goal sooner in environments with various numbers of goals and of differing sizes in an average time of 1.42 seconds, whereas a current state-of-the-art approach often breaches a 10 minute timeout.
Towards Quicker Probabilistic Recognition with Multiple Goal Heuristic Search
TLDR
A single execution of a planner will potentially speed up the recognition process using the original method, which also maintains the sacrificed properties and improves some of the assumptions made by Ram´ırez and Geffner.
Cost-Based Goal Recognition in Navigational Domains
TLDR
This extended version of earlier work generalises the framework to the continuous domain and discusses the results, including the conditions under which the findings can be generalised back to goal recognition in general task-planning.
Watching and Acting Together: Concurrent Plan Recognition and Adaptation for Human-Robot Teams
TLDR
This work introduces Pike, an executive for human-robot teams, that allows the robot to continuously and concurrently reason about what a human is doing as execution proceeds, as well as adapt appropriately, resulting in a mixed-initiative execution where humans and robots interact fluidly to complete task goals.
Action Selection for Transparent Planning
TLDR
A novel framework to formalize and solve transparent planning tasks by executing actions selected in a suitable and timely fashion by proposing an action selection strategy via on-line planning that seeks actions to quickly convey the goal being pursued to an observer assumed to fit a given stereotype.
Plan Recognition in Continuous Domains
TLDR
It is shown that through mirroring, a formalization of recognition problems which admits continuous environments, as well as discrete domains, the authors can apply continuous-world motion planners in plan recognition through generalizing plan-recognition by planning.
Plan-Recognition as Planning in Continuous and Discrete Domains
TLDR
This work provides a formalization of recognition problems which admits continuous environments, as well as discrete domains, and shows that through mirroring— generalizing plan-recognition by planning—the authors can apply continuous-world motion planners in plan recognition.
Goal Recognition Design in Deterministic Environments
TLDR
The worst case distinctiveness (WCD) measure is suggested, which represents the maximal cost of a path an agent may follow before its goal can be inferred by a goal recognition system.
...
...

References

SHOWING 1-10 OF 26 REFERENCES
Probabilistic Plan Recognition Using Off-the-Shelf Classical Planners
TLDR
This work shows that the problem of probabilistic plan recognition can be solved efficiently using classical planners provided that the probability of a partially observed execution given a goal is defined in terms of the cost difference of achieving the goal under two conditions: complying with the observations, and not complying with them.
Concurrent Plan Recognition and Execution for Human-Robot Teams
TLDR
Pike is introduced, an executive for human-robot teamwork that quickly adapts and infers intent based on the preconditions of actions in the plan, temporal constraints, unanticipated disturbances, and choices made previously (by either robot or human).
A Planning Approach to the Recognition of Multiple Goals
TLDR
A novel logic‐based approach to solve the multigoal recognition problem efficiently, without the need of plan libraries, using a state‐of‐the‐art heuristic search planner LAMA, and presents a bilevel probabilistic plan recognition approach.
Combining Plan Recognition, Goal Reasoning, and Planning for Cooperative Task Behaviour
TLDR
A framework for integrated plan recognition, goal reasoning, and planning, to produce cooperative behaviour for one agent to help another agent by proposing a set of subgoals to be achieved is presented.
Plan Recognition as Planning
In this work we aim to narrow the gap between plan recognition and planning by exploiting the power and generality of recent planning algorithms for recognizing the set G* of goals G that explain a
Plan Recognition as Planning Revisited
TLDR
This paper proposes to extend previous work to address observations over fluents, better address unreliable observations, and recognize plans in addition to goals, and approximate the posterior probabilities of generated plans by taking into account the combined costs that include penalties for missing or noisy observations.
Ordered Landmarks in Planning
TLDR
This work extends Koehler and Hoffmann's definition of reasonable orders between top level goals to the more general case of landmarks and shows how landmarks can be found, how their reasonable orders can be approximated, and how this information can be used to decompose a given planning task into several smaller sub-tasks.
Learning interaction for collaborative tasks with probabilistic movement primitives
TLDR
This paper introduces the use of Probabilistic Movement Primitives (ProMPs) to devise an interaction method that both recognizes the action of a human and generates the appropriate movement primitive of the robot assistant.
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response
TLDR
This work represents each possible future using an anticipatory temporal conditional random field (ATCRF) that models the rich spatial-temporal relations through object affordances and represents each ATCRF as a particle and represents the distribution over the potential futures using a set of particles.
Goal Recognition Design
TLDR
A way to reduce the wcd of a model by limiting the set of available actions an agent can perform and provide a method for calculating the optimal set of actions to be removed from the model is proposed.
...
...