Research
Research projects exploring Reinforcement Learning, Pro-Social Behaviours, and Multi-Modal Embedded Systems.
Publications
Explore-Exploit Behaviors During Rat-Robot Interactions Optimize Social and Spatial Security
2025 IEEE International Conference on Development and Learning
Each time an individual enters an environment, they must sample that environment in order to understand the potential hazards and rewards.
The uncertainty that comes with exploratory behavior can be stressful. An individual must learn to regulate their internal states to more flexibly process the outside world. One strategy for reducing risk in searching uncertain environments is establishing safe spots that can be frequently revisited in order to evaluate recently encountered information and to regulate stress that can build with social encounters and uncertainty. Engaging in this process with trusted social partners can help to mitigate stress, whereas encountering unknown others can induce stress. We seek to characterize how rodents' balances between exploration and regulation changes in the presence of social others and potential threats such as a novel robot.
Interactive neurorobotics: Behavioral and neural dynamics of agent interactions
Frontiers in Psychology, 2022; Sec. Cognitive Science
Interactive neurorobotics is a subfield which characterizes brain responses evoked during interaction with a robot, and their relationship with the behavioral responses.
Gathering rich neural and behavioral data from humans or animals responding to agents can act as a scaffold for the design process of future social robots. This research seeks to study how organisms respond to artificial agents in contrast to biological or inanimate ones. This experiment uses the novel affordances of the robotic platforms to investigate complex dynamics during minimally structured interactions that would be difficult to capture with classical experimental setups. We then propose a general framework for such experiments that emphasizes naturalistic interactions combined with multimodal observations and complementary analysis pipelines that are necessary to render a holistic picture of the data for the purpose of informing robotic design principles. Finally, we demonstrate this approach with an exemplar rat–robot social interaction task which included simultaneous multi-agent tracking and neural recordings.
Robotic Exploratory Control Via Subcortical Oscillations [NON-PRESENTED]
11th International Brain-Computer Interface Meeting 2025
Navigation through real-world environments remains a difficult task in intelligent robotics, due to a constantly changing landscape of potential hazards and new information
The current research investigates the effectiveness of neural oscillations in these brain regions as control signals for robotic navigation, using the natural hierarchy of rodent subcortical activity as a decision-making architec- ture for a self-monitoring neurorobotic system. Building such hierarchical control systems with self-regulatory mechanisms is crucial for developing intelligent robotics that perform natural tasks as biological agents do
Projects
Pirat Homebase
Robotics Using Bayesian Inference Lab | Chiba Lab
[Summary to be added]
- [Bullets to be added]
Pirat RL Regulation Optimization
Robotics Using Bayesian Inference Lab | Chiba Lab
[Summary to be added]
- [Bullets to be added]
AI Classroom
Center for Human Development | Cognitive Science Department
ABCD - Adolescent Brain Cognitive Development Study, UC San Diego Coordinating Center
[Summary to be added]
- [Bullets to be added]