Skip to main content
Menu
Back

Research at the Applied Artificial Intelligence group at the Oxford Robotics Institute

Research @ A2I

The research we do at A2I spans a diverse range of application areas, from robot perception to reinforcement learning and learning from demonstration. Our focus lies on exploring fundamental challenges at the intersection of machine learning, AI, and robotics.

Here’s a closer look at some of the exciting work going on in the group…

TactGen: Tactile Sensory Data Generation via Zero-Shot Sim-to-Real Transfer

Offline Adaptation of Quadruped Locomotion using Diffusion Models

Efficient skill acquisition for insertion tasks in obstructed environments

D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation
simulate radar forward and backward image

There And Back Again: Simulate Radar For Real World Applications

Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis

Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar

Permutation Invariance and Relational Reasoning in Multi-Object Tracking

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

Learning Robust, Distraction-Free Radar OdomLearning Robust, Distraction-Free Radar Odometry from Pose Informationetry from Pose Information

The Oxford Radar RobotCar Dataset

Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes

Deep Inverse Sensor Modelling in Radar

On the Limitations of Representing Functions on Sets

ShapeStacks: Giving Robots a Physical Intuition

Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects

Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments

TACO: Learning Decomposition via Temporal Alignment for Control