activity
20172020
most citedNeural Network Memory Architectures for Autonomous Robot Navigation

5 citations · 5 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CV2020

Place Recognition in Forests with Urquhart Tessellations

Guilherme V. Nardari, Avraham Cohen, Steven W. Chen +4

In this letter, we present a novel descriptor based on Urquhart tessellations derived from the position of trees in a forest. We propose a framework that uses these descriptors to…

cs.RO2019

SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory

Steven W. Chen, Guilherme V. Nardari, Elijah S. Lee +4

This paper describes an end-to-end pipeline for tree diameter estimation based on semantic segmentation and lidar odometry and mapping. Accurate mapping of this type of environment…

cs.CV2019

DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance

Yilun Zhang, Ty Nguyen, Ian D. Miller +4

Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution. Accurate depth se…

cs.CV2019

DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion

Shreyas S. Shivakumar, Ty Nguyen, Ian D. Miller +3

In this paper we propose a convolutional neural network that is designed to upsample a series of sparse range measurements based on the contextual cues gleaned from a high resoluti…

cs.RO2019

Decentralization of Multiagent Policies by Learning What to Communicate

James Paulos, Steven W. Chen, Daigo Shishika +1

Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication t…

cs.RO2018

Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association

Xu Liu, Steven W. Chen, Chenhao Liu +5

We present a cheap, lightweight, and fast fruit counting pipeline that uses a single monocular camera. Our pipeline that relies only on a monocular camera, achieves counting perfor…