*We're actively recruiting for Fall 2026.View positions
Research

Research Topics & Areas

Explore our active research areas and find where your interests align with ARENA Lab.

intermediate

Robot Navigation

Autonomous navigation systems for mobile robots in complex, dynamic environments. Classical planning to learning-based approaches.

ROS/ROS2Path PlanningSLAMMotion Planning
2 related projects
advanced

Social Navigation

Robots navigating among humans in a socially compliant manner. Understanding human motion patterns and social norms.

Human Motion PredictionSocial Force ModelsDeep RLHRI
2 related projects
intermediate

Simulation & Digital Twins

High-fidelity simulation environments for training and evaluating robot behaviors. Bridging the sim-to-real gap.

GazeboUnityIsaac SimDockerPython
2 related projects
advanced

Generative World Models

Generative models to learn environment dynamics for improved robot planning in unseen scenarios.

Diffusion ModelsVAEsTransformersPyTorch
1 related project
advanced

VLA/VLM for Robotics

Vision-Language-Action and Vision-Language Models enabling robots to follow natural language instructions.

Foundation ModelsComputer VisionNLPRobot Learning
intermediate

Human-Robot Interaction

Intuitive interfaces and behaviors for robots working alongside humans. User studies, trust, and safety.

User Study DesignStatisticsPsychologyROS
2 related projects
beginner

Benchmarking & Evaluation

Standardized benchmarks and metrics for evaluating robot navigation and social compliance.

Experiment DesignStatisticsSimulationData Analysis
1 related project
advanced

Sim-to-Real Transfer

Transferring policies trained in simulation to real robots. Domain adaptation, randomization, robustness.

Domain AdaptationRobot HardwareSimulationDeep RL
2 related projects
beginner

ARENA Platform

Contributing to the open-source ARENA simulation and benchmarking platform. Software development and community building.

PythonROSDockerSoftware EngineeringOpen Source
2 related projects
advanced

Embodied AI

Building AI systems that interact with the physical world through robotic embodiments. Combining perception, planning, and action.

Deep LearningReinforcement LearningRoboticsSimulation
2 related projects
Projects

Active Projects

active

Quadrupeds in Crowded Environments

Integration of quadrupeds into ArenaNav. Goal: deploy real quadruped robots at NUS campus and food centers!

PythonC++GazeboROS
active

Human Detection and Tracking (RGB-D)

Computer vision for human detection, tracking, action and social state detection communicated via ROS.

PythonCamerasComputer Vision
active

Arena-Web v3

Third version of our web-based benchmarking platform. Contribute new functionalities and participate in a paper.

JavaScriptReactDocker
View →
active

ArenaNav v4 – Core Platform

Fourth version of our core development and benchmarking platform. Always looking for students to contribute and participate in papers.

PythonC++ROS
View →
active

Photorealistic Simulation

Integration of ISAAC Gym simulation into ArenaNav and development of multimodal training approaches for navigation in crowds.

PythonIsaac GymROS
active

Robot Behavior Adaptation via Semantic Mapping

Navigation and behavior adaption for mobile robots based on semantic mapping and social interactions.

PythonC++GazeboROS
active

Multi Agent Reinforcement Learning

Multi-Agent-RL approaches for robots (homogeneous/heterogeneous) for tasks such as rescue or evacuation.

PythonOpenAI GymROS
active

LLM-based World Generation

Leveraging LLMs to dynamically generate millions of randomized worlds for training and benchmarking.

PythonMLLLMs