Papers
10
Total Citations
90
H-Index
5
About
Oscar Chang’s research lies at the intersection of robotics, computer vision, and artificial intelligence, with a particular focus on creating autonomous systems that learn and adapt through neural agents. His work consistently explores how deep neural networks and reinforcement learning can enable robots to perceive, track, and interact with their environments in real-time. His most cited paper, “A Novel Deep Neural Network that Uses Space-Time Features for Tracking and Recognizing a Moving Object” (2017, 39 citations), introduces a DNN that achieves reliable visual recognition of moving objects using autoencoding and substitutional reality to minimize tracking error. Chang has also made notable contributions to cooperative neural architectures, as seen in his 2010 work on evolving neural agents for vision-guided mobile robots (11 citations), and to self-programming and self-taught robotic systems, including a protein folding robot (2020, 8 citations) and a wise-up visual robot (2020, 6 citations). His recent work on Gemini Robotics (2025, 4 citations) addresses the challenge of translating large multimodal models into physical robotic agents, marking a significant step toward bringing AI into the physical world. With a career spanning over a decade, Chang’s research consistently pushes the boundaries of autonomous, learning-driven robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3A protein folding robot driven by a self-taught agent8 citations · 2020
- 4Self-programming Robots Boosted by Neural Agents6 citations · 2018
- 5A Wise Up Visual Robot Driven by a Self-taught Neural Agent6 citations · 2020
- 6
- 7Autonomous Robots and Behavior Initiators4 citations · 2018
- 8A Bio-Inspired Robot with Visual Perception of Affordances4 citations · 2015
- 9Gemini Robotics: Bringing AI into the Physical World4 citations · 2025
- 10A robotic eye controller based on cooperative neural agents3 citations · 2010