Embodied AI Research Areas

Autonomous Exploration, SLAM & Localization

Develops navigation systems that let autonomous agents explore unfamiliar environments, construct spatial representations, localize themselves, search for objects, and plan movement under embedded-resource constraints.

Paper 1: ROVER: Autonomous Open-Vocabulary Object Searching in Unexplored Environments Using VLM-Driven Scene Understanding

Paper 2: SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms

Paper 3: Efficient Neural Mapping for Localisation of Unmanned Ground Vehicles

Vision-Guided Perception, Manipulation & Grasping

Focuses on visual grounding, object understanding, distance estimation, grasp selection, and manipulation so embodied agents can interact reliably with objects and physical environments.

Paper 1: MVB-Grasp: Minimum-Volume-Box Filtering of Diffusion-based Grasps for Frontal Manipulation

Paper 2: GroundCount: Grounding Vision-Language Models with Object Detection for Hallucination-Free Counting

Paper 3: DECADE: Towards Designing Efficient-yet-Accurate Distance Estimation Modules for Collision Avoidance in Mobile Advanced Driver Assistance Systems

Brain-Controlled Assistive Robotics

Builds non-invasive neuro-driven assistive systems that translate EEG signals and voice commands into real-time prosthetic control, with emphasis on embedded operation, responsiveness, and accessibility.

Paper 1: BRAVE: Brain-Controlled Prosthetic Arm with Voice Integration and Embodied Learning for Enhanced Mobility

Paper 2: CognitiveArm: Enabling Real-Time EEG-Controlled Prosthetic Arm Using Embodied Machine Learning

Paper 3: MindArm: Mechanized Intelligent Non-Invasive Neuro-Driven Prosthetic Arm System

Adaptive Locomotion & Continual Autonomy

Investigates learning methods that help physical agents adapt their locomotion and behavior as environments and tasks change, including reinforcement learning, continual learning, and efficient autonomous-system architectures.

Paper 1: CuriousRL: Curiosity-Driven Reinforcement Learning for Adaptive Locomotion in Quadruped Robots

Paper 2: Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

Paper 3: TinyCL: An Efficient Hardware Architecture for Continual Learning on Autonomous Systems

Robust & Safe Autonomous Systems

Studies safety, security, and reliability of perception pipelines used by autonomous robots and vehicles under adverse weather, adversarial patches, backdoor attacks, and other real-world disruptions.

Paper 1: Robust ADAS: enhancing robustness of machine learning-based Advanced driver assistance systems for adverse weather

Paper 2: SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications

Paper 3: ShrinkBox: Backdoor Attack on Object Detection to Disrupt Collision Avoidance in Machine Learning-based Advanced Driver Assistance Systems