Deception in Autonomous Vehicle Decision Making in an Adversarial Environment

Singh, Rajdeep

doi:10.2514/6.2005-6152

Cited by 13 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the foundation of this approach, risk-sensitive estimation, has been reported by some of these authors in [38][39][40], this work contributes a major extension that accounts for broad range of information inputs, environmental complexity and near-real-time nature of the problem. Furthermore, this is the first work in which risk-sensitive estimation has been experimentally validated in rigorous and complex experiments that approximated a realistic problem domain.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Hypothesis-driven information fusion in adversarial, deceptive environments

et al. 2011

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

“…See [7,[38][39][40] for further discussion of the value function in a similar game problem. We now illustrate risk-sensitive estimation using a simple example.…”

Section: Risk-sensitive Controller Theorymentioning

confidence: 99%

Hypothesis-driven information fusion in adversarial, deceptive environments

et al. 2011

Self Cite

View full text Add to dashboard Cite

“…We note that, by ( 5)-( 6), the optimal deception problem is a reward maximization problem on the MDP M = (S×B, A, P ), where P is given by (6). With such a model, it is well-known that the optimal policy π * is memoryless, i.e., π * t depends solely on s t , B t , and t, and Problem 7 is solvable by previously known and extensively discussed methods (see, e.g., [19] for a detailed study).…”

Section: A Optimal Deceptive Policymentioning

confidence: 99%

“…The concept of deception is naturally present in a variety of contexts that have an adversarial element. Examples include cybersecurity [1]- [3], bio-inspired robotics [4], genetic algorithms [5], vehicle decision making [6], warfare strategy -a particularly voluminous study of the role of deception in war has been made in [7] -and interpersonal relationships [8]. A deceptive strategy employed by an agent in an adversarial setting rests on dual goals of the agent: 1) achieving its objective, 2) modifying the adversary's beliefs about the nature of that objective -for instance, objective location, distance, or reward attained at an objective.…”

Section: Introductionmentioning

confidence: 99%

Deception in Optimal Control

Ornik

Topcu

2018

2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)

View full text Add to dashboard Cite

In this paper, we consider an adversarial scenario where one agent seeks to achieve an objective and its adversary seeks to learn the agent's intentions and prevent the agent from achieving its objective. The agent has an incentive to try to deceive the adversary about its intentions, while at the same time working to achieve its objective. The primary contribution of this paper is to introduce a mathematically rigorous framework for the notion of deception within the context of optimal control. The central notion introduced in the paper is that of a belief-induced reward: a reward dependent not only on the agent's state and action, but also adversary's beliefs. Design of an optimal deceptive strategy then becomes a question of optimal control design on the product of the agent's state space and the adversary's belief space. The proposed framework allows for deception to be defined in an arbitrary control system endowed with a reward function, as well as with additional specifications limiting the agent's control policy. In addition to defining deception, we discuss design of optimally deceptive strategies under uncertainties in agent's knowledge about the adversary's learning process. In the latter part of the paper, we focus on a setting where the agent's behavior is governed by a Markov decision process, and show that the design of optimally deceptive strategies under lack of knowledge about the adversary naturally reduces to previously discussed problems in control design on partially observable or uncertain Markov decision processes. Finally, we present two examples of deceptive strategies: a "cops and robbers" scenario and an example where an agent may use camouflage while moving. We show that optimally deceptive strategies in such examples follow the intuitive idea of how to deceive an adversary in the above settings.

show abstract

“…The motivational application here is the military command and control (C 2 ) problem for air operations, with unmanned/uninhabited air vehicles (UAVs). See [2], [5], [16], [21], [28], [31], [24], [25] for related information. This application has specific characteristics such that we will be able to construct a reasonable problem formulation which is particularly nice from the point of view of analysis and computation.…”

Section: Introductionmentioning

confidence: 99%

Robustness Against Deception in Unmanned Vehicle Decision Making

McEneaney¹,

Singh²

2007

Proceedings of the 3rd International Workshop on Multi-Agent Robotic Systems

View full text Add to dashboard Cite

We are motivated by the tasking problem for UAVs in an adversarial environment. In particular, we consider the problem where, in addition to purely random noise in the observation process, the opponent may be applying deception as a means to cause us to make poor tasking choices. The standard approach would be to apply the feedback-optimal controls for the fully-observed game, to a maximum-likelihood state estimate. We find that such an approach is highly suboptimal. A second approach is through a concept taken from risk-sensitive control. For the third approach, we formulate and solve the problem directly as a partially-observed stochastic game. A chief problem with such a formulation is that the information state for the player with imperfect information is a function over the space of probability distributions (a function over a simplex), and so infinite-dimensional. However, under certain conditions, we find that the information state is finite-dimensional. Computational tractability is greatly enhanced. A simple example is considered, and the three approaches are compared. We find that the third approach is yields the best results (for such a case), although computational complexity may lead to use of the second approach on larger problems.

show abstract

Deception in Autonomous Vehicle Decision Making in an Adversarial Environment

Cited by 13 publications

References 10 publications

Hypothesis-driven information fusion in adversarial, deceptive environments

Hypothesis-driven information fusion in adversarial, deceptive environments

Deception in Optimal Control

Robustness Against Deception in Unmanned Vehicle Decision Making

Contact Info

Product

Resources

About