Juntong Peng

Juntong Peng | 彭钧桐

Hi! I am a first-year Ph.D. student in Purdue ECE, co-advised by Prof. Yaobin Chen and Prof. Ziran Wang.

I received my bachelor degree in information enginnering from Shanghai Jiao Tong University, advised by Prof. Siheng Chen. I have also spent a wonderful summer at the Department of Computer Science, Purdue University as a research intern, advised by Prof. Aniket Bera.

Research

My research focuses on autonomous driving and computer vision, specifically on end-to-end driving and human-AI teaming.

Previously, I worked on the efficiency aspect of collaborative perception and making use of the complementary strengths of agents in heterogeneous systems.

Publications

Communication-Efficient Collaborative Perception via Information Filling with Codebook
Yue Hu, Juntong Peng, Sifei Liu, Junhao Ge, Si Liu, Siheng Chen
CVPR, 2024

We proposed a Communication-Efficient collaboration method, which enhances the tradeoff between performance and communication cost by optimizing information selection and representation.

Graph-based Decentralized Task Allocation for Multi-Robot Target Localization
Juntong Peng, Hrishikesh Viswanath, Aniket Bera
RAL, 2024
arXiv

We proposed a graph neural network based method to dynamically allocate tasks to different robots. We utilized the comparative advantages of different robots to improve the overall performance of the system.

Communication-Efficient Multi-Agent 3D Detection via Hybrid Collaboration
Yue Hu, Juntong Peng, Yunqiao Yang, Xiaoqi Qin, Zhiyong Feng, Wenjun Zhang, Siheng Chen
2024, Under review

We utilized the confidence and uncertainty of single perception to guide the information sharing process, combining the benefits of both sparse and dense information form. Our method consumes far less communication resources than the previous SOTA.

Compatible transformer for irregularly sampled multivariate time series
Yuxi Wei, Juntong Peng, Tong He, Chenxin Xu, Jian Zhang, Shirui Pan, Siheng Chen
ICDM, 2023
project page / arXiv

We proposed a transformer-based model to handle irregularly sampled multivariate time series. Our model is inspired by the correlation between multi-agent trajectories.

Service & Teaching

Reviewer: IEEE Robotics and Automation Letters

2023

Reviewer: IEEE Internet of Things Journal

2023

TA: CS1108 - Introduction to Data Science, fall 2023

Fall, 2023

Internship

Strategic Intern @ Corporate Research, Robert Bosch GmbH

Jan. 2024 - Jun. 2024

Working on the topic of reliable distributed system for V2X collaboration.