Papers

Uncertainty-Driven Dense Two-View Structure From Motion
We present a modular and training-free solution, which embraces more classic approaches, to tackle the object goal navigation problem.
[Webpage][Paper][Code]

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning
We propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic.
[Paper][Code]

Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing
We use contrastive learning to extract robust feature representations from the input images and leverage a two-stage learning-by-cheating framework for training a neural network policy.
[Webpage][Paper][Code]