D
Debadeepta Dey
Researcher at Microsoft
Publications - 75
Citations - 3845
Debadeepta Dey is an academic researcher from Microsoft. The author has contributed to research in topics: Submodular set function & Computer science. The author has an hindex of 23, co-authored 68 publications receiving 2707 citations. Previous affiliations of Debadeepta Dey include Carnegie Mellon University.
Papers
More filters
Posted Content
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
TL;DR: A new simulator built on Unreal Engine that offers physically and visually realistic simulations for autonomous vehicles in real world and that is designed from the ground up to be extensible to accommodate new types of vehicles, hardware platforms and software protocols.
Book ChapterDOI
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
TL;DR: In this paper, the authors present a new simulator built on Unreal Engine that offers physically and visually realistic simulations for autonomous vehicles in real-world environments, including a physics engine that can operate at a high frequency for real-time hardware-in-the-loop (HITL) simulations with support for popular protocols (e.g., MavLink).
Proceedings ArticleDOI
Learning monocular reactive UAV control in cluttered natural environments
Stephane Ross,Narek Melik-Barkhudarov,Kumar Shaurya Shankar,Andreas Wendel,Debadeepta Dey,J. Andrew Bagnell,Martial Hebert +6 more
TL;DR: A system that navigates a small quadrotor helicopter autonomously at low altitude through natural forest environments using only a single cheap camera to perceive the environment, and using recent state-of-the-art imitation learning techniques to train a controller that can avoid trees by adapting the MAVs heading.
Proceedings ArticleDOI
Submodular Trajectory Optimization for Aerial 3D Scanning
Mike Roberts,Shital Shah,Debadeepta Dey,Anh Truong,Sudipta N. Sinha,Ashish Kapoor,Pat Hanrahan,Neel Joshi +7 more
TL;DR: In this article, the authors present an automatic method to generate drone trajectories, such that the imagery acquired during the flight will later produce a high-fidelity 3D model.
Proceedings ArticleDOI
Classification of plant structures from uncalibrated image sequences
TL;DR: The feasibility of recovering fine-scale plant structure in 3D point clouds by leveraging recent advances in structure from motion and3D point cloud segmentation techniques is demonstrated, significantly improving over the baseline performance achieved using established methods.