Openings at the BrainX Group for Embodied AI Systems and Robotic Learning
3110
Openings at the BrainX Group for Embodied AI Systems and Robotic Learning
Multiple Master's and Ph.D. positions with full RA/TA support are available in Hongyu An's research group (sites.google.com). Hongyu is an assistant professor at the Electrical and Computer Engineering Department of Michigan Tech. His research interest mainly focuses on Neuromorphic Computing, Robotic Learning, and Medical Applications.
The BrainX group (sites.google.com) is recruiting motivated Master’s and PhD students who are passionate about brain-inspired artificial intelligence, neuromorphic computing, robotic learning, and cross-disciplinary research. Our mission is to build intelligent systems that learn, explore, and adapt like animals, and to uncover the fundamental principles of learning and memory in biological neural systems.
Research Thrusts
1 Neuromorphic Embodied AI System
Our lab is developing a new class of intelligent systems that tightly couple perception, spatial navigation, associative learning, and memory. We build biologically grounded neural modules that allow robots to actively explore the environment, form internal representations from visual and spatial cues, and acquire new skills through self-learning experience. Current research includes:
Grid cell and place cell models for spatial navigation
Orientation cell and color cell models for robust visual perception
Associative learning and memory systems
Self learning and decision-making mechanisms
2 Biological Validation with Rodent Neural Data
A major goal of the lab is to ensure that our neuromorphic robot and embodied AI systems remain aligned with real biological neural activity and self-learning behaviors in rodents. Beyond simulated and robotic experiments, we validate our model output against rodent hippocampal neural recordings.
In various spatial tasks, our system generates visual driven place cell firing patterns that mirror rodent activity, providing strong evidence of biological consistency.
Our lab maintains a close collaboration with the University of Southern California. Together, we are developing a joint research program on “rodent to robot calibration,” integrating real hippocampal neural data with our neuromorphic robot models.
Collaborative activities include
Recording rodent CA1 and CA3 activity during spatial exploration
Calibrating neuromorphic robot models using rodent firing patterns
Joint validation of learning, memory, and navigation consistency across biological and robotic systems
This partnership provides students with the opportunity to
Learn cutting-edge hippocampal neural signal processing
Work with real rodent electrophysiology data
Align neuromorphic robot models directly with animal data
3 Why Join Our Lab
Strong integration of neuromorphic models with real robotic behavior
True multimodal learning in real-world environments
Biological grounding through rodent neural data
Collaborative research environment with USC
Ideal for students interested in both neuroscience and artificial intelligence
Recruited students will receive hands-on training in surgical procedures and participate in experimental studies involving rodents. More information can be found at sites.google.com They may also have internship opportunities with collaborators at top institutions such as USC and UC Davis.
4 The ideal candidates are expected to have extensive experience in
Understanding ROS
Robotic sensors, e.g., Lidar, cameras, etc.
Basic understanding of deep learning, neural networks
Programming experience in one or more of the following languages: Python, MatLab, etc.
Programming experience on deep learning platforms: Pytorch, TensorFlow, etc.
Ability to communicate effectively (both verbal and written)
If interested, please send me your CV, transcript(s), GRE, TOEFL (international applicants only), and sample publications if applicable to the email address: 1point3acres.com
Other detailed requirements from the department/college can be found at mtu.edu
Multiple Master's and Ph.D. positions with full RA/TA support are available in Hongyu An's research group (sites.google.com). Hongyu is an assistant professor at the Electrical and Computer Engineering Department of Michigan Tech. His research interest mainly focuses on Neuromorphic Computing, Robotic Learning, and Medical Applications.
The BrainX group (sites.google.com) is recruiting motivated Master’s and PhD students who are passionate about brain-inspired artificial intelligence, neuromorphic computing, robotic learning, and cross-disciplinary research. Our mission is to build intelligent systems that learn, explore, and adapt like animals, and to uncover the fundamental principles of learning and memory in biological neural systems.
Research Thrusts
1 Neuromorphic Embodied AI System
Our lab is developing a new class of intelligent systems that tightly couple perception, spatial navigation, associative learning, and memory. We build biologically grounded neural modules that allow robots to actively explore the environment, form internal representations from visual and spatial cues, and acquire new skills through self-learning experience. Current research includes:
Grid cell and place cell models for spatial navigation
Orientation cell and color cell models for robust visual perception
Associative learning and memory systems
Self learning and decision-making mechanisms
2 Biological Validation with Rodent Neural Data
A major goal of the lab is to ensure that our neuromorphic robot and embodied AI systems remain aligned with real biological neural activity and self-learning behaviors in rodents. Beyond simulated and robotic experiments, we validate our model output against rodent hippocampal neural recordings.
In various spatial tasks, our system generates visual driven place cell firing patterns that mirror rodent activity, providing strong evidence of biological consistency.
Our lab maintains a close collaboration with the University of Southern California. Together, we are developing a joint research program on “rodent to robot calibration,” integrating real hippocampal neural data with our neuromorphic robot models.
Collaborative activities include
Recording rodent CA1 and CA3 activity during spatial exploration
Calibrating neuromorphic robot models using rodent firing patterns
Joint validation of learning, memory, and navigation consistency across biological and robotic systems
This partnership provides students with the opportunity to
Learn cutting-edge hippocampal neural signal processing
Work with real rodent electrophysiology data
Align neuromorphic robot models directly with animal data
3 Why Join Our Lab
Strong integration of neuromorphic models with real robotic behavior
True multimodal learning in real-world environments
Biological grounding through rodent neural data
Collaborative research environment with USC
Ideal for students interested in both neuroscience and artificial intelligence
Recruited students will receive hands-on training in surgical procedures and participate in experimental studies involving rodents. More information can be found at sites.google.com They may also have internship opportunities with collaborators at top institutions such as USC and UC Davis.
4 The ideal candidates are expected to have extensive experience in
Understanding ROS
Robotic sensors, e.g., Lidar, cameras, etc.
Basic understanding of deep learning, neural networks
Programming experience in one or more of the following languages: Python, MatLab, etc.
Programming experience on deep learning platforms: Pytorch, TensorFlow, etc.
Ability to communicate effectively (both verbal and written)
If interested, please send me your CV, transcript(s), GRE, TOEFL (international applicants only), and sample publications if applicable to the email address: 1point3acres.com
Other detailed requirements from the department/college can be found at mtu.edu
