• Corpus ID: 102352312

To Monitor Or Not: Observing Robot's Behavior based on a Game-Theoretic Model of Trust

  title={To Monitor Or Not: Observing Robot's Behavior based on a Game-Theoretic Model of Trust},
  author={Sailik Sengupta and Zahra Zahedi and S. Kambhampati},
In scenarios where a robot generates and executes a plan, there may be instances where this generated plan is less costly for the robot to execute but incomprehensible to the human. When the human acts as a supervisor and is held accountable for the robot’s plan, the human may be at a higher risk if the incomprehensible behavior is deemed to be unsafe. In such cases, the robot, who may be unaware of the human’s exact expectations, may choose to do (1) the most constrained plan (i.e. one… 


Explicable Robot Planning as Minimizing Distance from Expected Behavior
This paper proposes to address the issue of explicable robot plans by learning a distance function that can accurately model the notion of explicability, and develops an anytime search algorithm that can use this measure in its search process to come up with progressively explicable plans.
Explanations as Model Reconciliation - A Multi-Agent Perspective
In this paper, we demonstrate how a planner (or a robot as an embodiment of it) can explain its decisions to multiple agents in the loop together considering not only the model that it used to come
The Off-Switch Game
It is concluded that giving machines an appropriate level of uncertainty about their objectives leads to safer designs, and it is argued that this setting is a useful generalization of the classical AI paradigm of rational agents.
Plan explicability and predictability for robot task planning
The notions of plan explicability and predictability are introduced and can be used by agents to proactively choose or directly synthesize plans that are more explicable and predictable to humans.
Playing games for security: an efficient exact algorithm for solving Bayesian Stackelberg games
This paper considers Bayesian Stackelberg games, in which the leader is uncertain about the types of adversary it may face, and presents an efficient exact algorithm for finding the optimal strategy for the leader to commit to in these games.
Grandpa Hates Robots - Interaction Constraints for Planning in Inhabited Environments
An approach for automatically generating plans that are conformant wrt.
Towards Modeling Trust Based Decisions: A Game Theoretic Approach
A game theoretic model that is specifically tuned for decision support on a whole host of actions, based on specified thresholds of risk, and extended to the incentive trust model where entities can offer incentives to be trusted in a multi-period transaction.
Legibility and predictability of robot motion
The findings indicate that for robots to seamlessly collaborate with humans, they must change the way they plan their motion, and a formalism to mathematically define and distinguish predictability and legibility of motion is developed.
Robust planning with incomplete domain models
The Fast Downward Planning System
  • M. Helmert
  • Computer Science, Mathematics
    J. Artif. Intell. Res.
  • 2006
A full account of Fast Downward's approach to solving multivalued planning tasks is given and a new non-heuristic search algorithm called focused iterative-broadening search, which utilizes the information encoded in causal graphs in a novel way is presented.