Jinkun Wang

About

Jinkun Wang is a robotics and autonomous systems researcher whose work sits at the intersection of probabilistic mapping, information-theoretic planning, and machine learning for mobile robots. His research has made significant contributions to two core challenges in autonomous robotics: building rich, accurate maps of unknown environments and enabling robots to explore those environments intelligently and efficiently. Wang's early and most influential work—"Information-theoretic exploration with Bayesian optimization" (132 citations)—established a principled framework for guiding mobile robots toward maximally informative sensing locations, a problem central to autonomous navigation. Complementing this, his series of papers on Gaussian process occupancy mapping and Bayesian generalized kernel inference (82 and 50 citations, respectively) advanced the state of the art in producing descriptive 3D maps from sparse, noisy sensor data. His later research embraced deep reinforcement learning, with graph-based exploration policies that handle localization uncertainty in real-time, including zero-shot transfer across environments—a particularly forward-looking achievement. His work on underwater autonomous exploration and lidar super-resolution further demonstrates the breadth of his impact across challenging real-world domains. Collectively, Wang's publications have accumulated over 560 citations, reflecting their lasting influence on the robotics research community.

Research Focus

Key Achievements

Top Papers

1. 1
   Information-theoretic exploration with Bayesian optimization

   132 citations · 2016
2. 2
   Simulation-based lidar super-resolution for ground vehicles

   83 citations · 2020
3. 3
   Fast, accurate gaussian process occupancy maps via test-data octrees and nested Bayesian fusion

   82 citations · 2016
4. 4
   Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs

   74 citations · 2020
5. 5
   Learning-Aided 3-D Occupancy Mapping With Bayesian Generalized Kernel Inference

   50 citations · 2019
6. 6
   Virtual Maps for Autonomous Exploration of Cluttered Underwater Environments

   41 citations · 2022
7. 7
   Bayesian generalized kernel inference for occupancy map prediction

   37 citations · 2017
8. 8
   Inference-Enabled Information-Theoretic Exploration of Continuous Action Spaces

   23 citations · 2017
9. 9
   Autonomous Exploration with Expectation-Maximization

   22 citations · 2019
10. 10
    Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty

    18 citations · 2021

Key Collaborators

Contact & Links