output
20152020
most citedAstraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications

200 citations

7 papers

cs.CV2020★ 65 cited

Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry

Guangming Wang, Chi Zhang, Hesheng Wang +3

In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames a…

cs.LG2019★ 200 cited

Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications

Moming Duan, Duo Liu, Xianzhang Chen +4

Federated learning (FL) is a distributed deep learning method which enables multiple participants, such as mobile phones and IoT devices, to contribute a neural network model while…

cs.RO2019

Real-time Trajectory Generation for Quadrotors using B-spline based Non-uniform Kinodynamic Search

Lvbang Tang, Hesheng Wang, Peng Li +1

In this paper, we propose a time-efficient approach to generate safe, smooth and dynamically feasible trajectories for quadrotors in obstacle-cluttered environment. By using the un…

eess.SY2018★ 13 cited

Towards Manipulability of Interactive Lagrangian Systems

Hanlei Wang

This paper investigates manipulability of interactive Lagrangian systems with parametric uncertainty and communication/sensing constraints. Two standard examples are teleoperation…

eess.SY2016★ 56 cited

Dynamic Modularity Approach to Adaptive Inner/Outer Loop Control of Robotic Systems

Hanlei Wang, Wei Ren, Chien Chern Cheah +2

Modern applications of robotics typically involve a robot control system with an inner PI (proportional-integral) or PID (proportional-integral-derivative) control loop and an oute…

eess.SY2015★ 3 cited

On Convergence Rate of Leader-Following Consensus of Linear Multi-Agent Systems with Communication Noises

Long Cheng, Yunpeng Wang, Wei Ren +2

This note further studies the previously proposed consensus protocol for linear multi-agent systems with communication noises in [15], [16]. Each agent is allowed to have its own t…