NewEvery arXiv paper, its researchers & institutions — mapped.
the archive

#imitation learning

6 results
cs.RO2019

Agile Autonomous Driving using End-to-End Deep Imitation Learning

Yunpeng Pan, Ching-An Cheng, Kamil Saigol +4

The paper introduces an end-to-end deep imitation learning system that enables high-speed off‑road autonomous driving using only low‑cost sensors, by training a neural network to m…

#autonomous driving#imitation learning#end-to-end control#off-road navigation
cs.RO2019

Learning Vision-based Flight in Drone Swarms by Imitation

Fabian Schilling, Julien Lecoeur, Fabrizio Schiano +1

The paper introduces a fully decentralized, vision‑only control method for drone swarms using imitation learning, where a small CNN maps raw omnidirectional images to 3‑D velocity…

#drone swarms#vision-based control#imitation learning#decentralized navigation
cs.CV2019

Early Fusion for Goal Directed Robotic Vision

Aaron Walsman, Yonatan Bisk, Saadia Gabriel +4

The paper proposes EarlyFusion vision models that condition on a robot's goal to create task‑specific visual representations, enabling faster learning, lower parameter use, and gre…

#goal‑directed vision#early fusion#robotic perception#imitation learning
cs.LG2019

Discovering hierarchies using Imitation Learning from hierarchy aware policies

Ameet Deshpande, Harshavardhan Kamarthi, Balaraman Ravindran

The paper examines options learned by the Deep Discovery of Options (DDO) algorithm from expert demonstrations, identifies that these options often terminate too early, and propose…

#hierarchical reinforcement learning#imitation learning#option discovery#policy evaluation
cs.RO2019

Flying through a narrow gap using neural network: an end-to-end planning and control approach

Jiarong Lin, Luqi Wang, Fei Gao +2

The paper introduces an end‑to‑end neural network that directly maps a drone’s perception of a tilted narrow gap to thrust and attitude commands, using imitation learning followed…

#drone navigation#end-to-end learning#imitation learning#reinforcement learning
cs.RO2019

DeepMoTIon: Learning to Navigate Like Humans

Mahmoud Hamandi, Mike D'Arcy, Pooyan Fazli

The paper introduces DeepMoTIon, a deep learning system that enables robots to navigate crowds by imitating human motion, using LiDAR data to predict human-like velocities and reac…

#human-aware navigation#imitation learning#lidar perception#crowd navigation