Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Posts

portfolio

Development of Reconnaissance Robots Having Amphibious Mobility

Leading the perception stack for a robot that crosses between water and land, where the sensor domain shifts abruptly at the shoreline. Targets: 5 object classes at 65% detection and 90% recognition rate.

Acquisition and Labelling of Robot Manipulation Task Data in Laboratory Environments

Leading the design and collection of a labelled manipulation dataset — trajectories, contacts and object states — for learning-based robot manipulation.

Development of Tactile Intelligence in Robotic Hands Based on Tactile Data Learning for Manipulating Irregular Multiple Types of Objects

Learning a tactile representation that lets a multi-fingered hand grasp and reorient unseen, irregular objects without a prior CAD model. Targets: 85% peg-in-hole success over 5 object types, 90% object recognition.

PoC of 3D Model-based Object Recognition and AR Visualisation with an RGB-D Camera

Real-time registration of observed RGB-D parts against reference CAD models, driving an AR overlay for on-line industrial part identification and pose estimation.

Development of Micro Intelligent Drone for Autonomous Mission in Communication/GPS-denied Environments

RGB-IR-LiDAR sensor-fusion object detection from drone views, plus construction of the multi-modal database behind it. Targets: ≥0.85 mAP@0.5 on targets as small as 30×30 px, holding ≥0.65 mAP under image degradation.

Hair and Dust Recognition for Robot Vacuum Cleaners

On-device segmentation of hair and dust for a domestic robot vacuum, constrained to ≤5M parameters — ≥85% pixel accuracy at ≤10% false-positive rate, trained on a purpose-built 10K-image dataset.

Test-time Domain Adaptation for Mobile Robot Operation under Adverse Conditions such as Varying Weather

Led a two-step continual test-time adaptation method that keeps a mobile robot’s perception working as the input distribution drifts with the weather — 14% mean corruption error on CIFAR-10-C.

Development of Swarm USV Autonomous Navigation Algorithm

Maritime object detection and situational awareness feeding the navigation stack of a swarm of unmanned surface vehicles.

Room Layout Detection for Estimating the Home Environment

A ceiling segmentation model and dataset for robust floor-plan generation under heavy occlusion, at 85% layout pixel accuracy — the work behind SMRNet.

Deep Reinforcement Learning-based Human-Robot Collaboration for Unstructured Tasks such as Assembly

Closing the simulation-to-reality gap so that policies trained in simulation transfer to a real collaborative assembly cell.

Electrical Facility Safety Management through Life-cycle History Management

Deep-learning detection and type classification of corona discharge for automated cable safety inspection — later published at IAS 2023 and awarded the MOTIE Minister’s Award.

Applying Artificial Intelligence to Underground Facility Exploration

Object detection inside low-light underground power tunnels, made robust at the feature level via patch-level cycle consistency rather than by enhancing the image — light enough to run on-board a robot with no comms. Built the cart-mounted multi-camera capture rig and authored the contract report.