• Corpus ID: 35501484

Towards Quicker Probabilistic Recognition with Multiple Goal Heuristic Search

@inproceedings{Freedman2018TowardsQP,
  title={Towards Quicker Probabilistic Recognition with Multiple Goal Heuristic Search},
  author={Richard Gabriel Freedman and Yi Ren Fung and Roman Ganchin and Shlomo Zilberstein},
  booktitle={AAAI Workshops},
  year={2018}
}
Referred to as an approach for either plan or goal recognition, the original method proposed by Ram´ırez and Geffner introduced a domain-based approach that did not need a library containing specific plan instances. This introduced a more generalizable means of representing tasks to be recognized, but was also very slow due to its need to run simulations via multiple executions of an off-the-shelf classical planner. Sev- eral variations have since been proposed for quicker recognition, but each… 

Figures from this paper

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.
Landmark-Based Approaches for Goal Recognition as Planning
Action trees for scalable goal recognition in robotic applications
TLDR
An early version of this work focuses on goal recognition using techniques from classical symbolic planning to form an Action Tree, and presents results which show improved goal recognition times, without compromising on accuracy.
Goal Recognition over Imperfect Domain Models
TLDR
This thesis develops novel goal recognition approaches over imperfect domains models by leveraging and adapting existing recognition approaches from the literature, and develops solution approaches that explicitly deal with two distinct types of imperfect domain models.
A Unifying Perspective of Plan, Activity, and Intent Recognition
TLDR
A generalized formalization of recognition that can be used in all three types of recognition is proposed and a perspective that emphasizes how PAIR applies to different aspects of the generative planning and execution process is proposed.
Action graphs for proactive robot assistance in smart environments
TLDR
Action Graphs are introduced to model the order constraints between actions in a kitchen domain to enable a robot to proactively assist humans by autonomously executing an action on their behalf.
A Study of Human-Robot Copilot Systems for En-route Destination Changing
TLDR
The problem of enroute destination changing for a self-driving car is introduced, and the effectiveness of human-robot copilot systems as a solution is studied, finding that they can complete the autonomous parking task more efficiently than human drivers can.

References

SHOWING 1-10 OF 19 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.
Heuristic Online Goal Recognition in Continuous Domains
TLDR
This paper presents an online recognition algorithm, where two heuristic decision points may be used to improve run-time significantly over existing work, and specifies heuristics for continuous domains, prove guarantees on their use, and empirically evaluate the algorithm over hundreds of experiments.
Integration of Planning with Recognition for Responsive Interaction Using Classical Planners
TLDR
This paper proposes an integration of planning with probabilistic recognition where each method uses intermediate results from the other as a guiding heuristic for recognition of the plan/goal in-progress as well as the interactive response.
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.
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
Landmark-Based Heuristics for Goal Recognition
TLDR
This paper develops two goal recognition heuristics that rely on information from planning landmarks that can recognize goals more accurately, and run orders of magnitude faster, than the current state-of-the-art.
Cost-Based Goal Recognition for Path-Planning
TLDR
It is shown that the probability distribution based on this technique is observation-independent and a revised formula is presented that achieves goal-recognition by reference to the agent's current location only.
SLIM: Semi-Lazy Inference Mechanism for Plan Recognition
TLDR
A new and efficient algorithm for online plan recognition called SLIM (Semi-Lazy Inference Mechanism), which combines both a bottom-up and top-down parsing processes, which allow it to commit only to the minimum necessary actions in real-time, but still provide complete hypotheses post factum.
Probabilistic Abduction for Plan Recognition
TLDR
A formal model of the construction of possible plans that could explain a set of observed actions, and the selection of one or more of them as providing the {\em best} explanation based upon probability theory is presented.
...
...