6 papers
Simultaneous Perception-Action Design via Invariant Finite Belief Sets
Michael Hibbard, Takashi Tanaka, Ufuk Topcu
Although perception is an increasingly dominant portion of the overall computational cost for autonomous systems, only a fraction of the information perceived is likely to be relev…
Entropy Maximization for Partially Observable Markov Decision Processes
Yagiz Savas, Michael Hibbard, Bo Wu +2
We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total…
On Minimizing Total Discounted Cost in MDPs Subject to Reachability Constraints
Yagiz Savas, Christos K. Verginis, Michael Hibbard +1
We study the synthesis of a policy in a Markov decision process (MDP) following which an agent reaches a target state in the MDP while minimizing its total discounted cost. The pro…
Point-Based Value Iteration and Approximately Optimal Dynamic Sensor Selection for Linear-Gaussian Processes
Michael Hibbard, Kirsten Tuggle, Takashi Tanaka
The problem of synthesizing an optimal sensor selection policy is pertinent to a variety of engineering applications ranging from event detection to autonomous navigation. We consi…
Minimizing the Information Leakage Regarding High-Level Task Specifications
Michael Hibbard, Yagis Savas, Zhe Xu +1
We consider a scenario in which an autonomous agent carries out a mission in a stochastic environment while passively observed by an adversary. For the agent, minimizing the inform…
Unpredictable Planning Under Partial Observability
Michael Hibbard, Yagiz Savas, Bo Wu +2
We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total…