171 citations · 937 across the 54 of their papers we have counts for
8 papers · 1 filter
Unadversarial Examples: Designing Objects for Robust Vision
Hadi Salman, Andrew Ilyas, Logan Engstrom +3
We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized. We develop a framework that leverages this capability t…
Helping Reduce Environmental Impact of Aviation with Machine Learning
Ashish Kapoor
Commercial aviation is one of the biggest contributors towards climate change. We propose to reduce environmental impact of aviation by considering solutions that would reduce the…
Adversarial Attacks on Optimization based Planners
Sai Vemprala, Ashish Kapoor
Trajectory planning is a key piece in the algorithmic architecture of a robot. Trajectory planners typically use iterative optimization schemes for generating smooth trajectories t…
Do Adversarially Robust ImageNet Models Transfer Better?
Hadi Salman, Andrew Ilyas, Logan Engstrom +2
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-tr…
AirSim Drone Racing Lab
Ratnesh Madaan, Nicholas Gyde, Sai Vemprala +7
Autonomous drone racing is a challenging research problem at the intersection of computer vision, planning, state estimation, and control. We introduce AirSim Drone Racing Lab, a s…
Safety Considerations in Deep Control Policies with Safety Barrier Certificates Under Uncertainty
Tom Hirshberg, Sai Vemprala, Ashish Kapoor
Recent advances in Deep Machine Learning have shown promise in solving complex perception and control loops via methods such as reinforcement and imitation learning. However, guara…
TartanAir: A Dataset to Push the Limits of Visual SLAM
Wenshan Wang, Delong Zhu, Xiangwei Wang +6
We present a challenging dataset, the TartanAir, for robot navigation tasks and more. The data is collected in photo-realistic simulation environments with the presence of moving o…
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
Hadi Salman, Mingjie Sun, Greg Yang +2
We present a method for provably defending any pretrained image classifier against adversarial attacks. This method, for instance, allows public vision API providers and u…