Ali Agha

TL;DR: A deep quantile regression framework for control is introduced that enforces probabilistic quantile bounds and quantifies epistemic uncertainty in learning-based control models.

TL;DR: This work proposes a modification to the value iteration recurrence, referred to as the soft value iteration network (SVIN), which relies on an internal soft policy model, where the policy is represented with a probability distribution over all possible actions, rather than a deterministic policy that returns only the best action.

TL;DR: This work model environmental uncertainty as a belief space Markov decision process and formulate the problem as a two-step stochastic dynamic program that is solved in a way that leverages the decomposed nature of the overall system.

TL;DR: NeBula as mentioned in this paper is an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states).

TL;DR: The never-ending human curiosity about exploring the universe is pushing the limits of robotic autonomy from remote-controlled to fully autonomous systems characterized by advanced learning, cognition, and reasoning for operating in completely unknown and unstructured environments.