Publications

Evolving Spiking Neural Networks for Nonlinear Control Problems Spiking Neural Networks are powerful computational modelling tools that have attracted much interest because of the bioinspired modelling of synaptic interactions between neurons. Most of the research employing spiking neurons has been non-behavioural and discontinuous. Comparatively, this paper presents a recurrent spiking controller that is capable of […]

Safe terrain probing method for multi-legged robots operating on brittle surfaces Multi-legged robots working in challenging environments are often required to walk on fragile terrain that may collapse upon traversal. We propose a method to test the robot’s next foothold for collapses without endangering it. In this method, the robot’s body is posed in a […]

Skeleton Driven Non-Rigid Motion Tracking and 3D Reconstruction This paper presents a method which can track and 3D reconstruct the non-rigid surface motion of human performance using a RGB-D camera. 3D reconstruction of marker-less human performance is a challenging problem due to the large range of articulated motions and considerable non-rigid deformations. Current approaches use […]

Dynamic Manipulation of Gear Ratio and Ride Height for a Novel Compliant Wheel using Pneumatic Actuators. This paper proposes a novel configurable wheel that exhibits desired properties of varied radius wheels. Positional manipulation of the centre hub is proposed and tested to achieve these desired characteristics of ‘virtual’ wheels in a physical system. The centre […]

After the success of ICRA 2018, which was held in Australia for the first time, our team is now gearing up to ICRA 2019. Happening in Montreal, Canada between 20-24 May, the team is proud to have six papers accepted at the conference: Local Descriptor for Robust Place Recognition using LiDAR Intensity Quantifying the Reality […]

Optimization-Based Terrain Analysis and Path Planning in Unstructured Environments Accurate environment representation is one of the key challenges in autonomous ground vehicle navigation in unstructured environments. We propose a real-time optimization based approach to terrain modeling and path planning in offroad and rough environments. Our method uses an irregular, hierarchical, graph-like environment model. A space-dividing tree is used to define […]

OVPC Mesh: 3D Free-space Representation for Local Ground Vehicle Navigation This paper presents a novel approach for local 3D environment representation for autonomous unmanned ground vehicle (UGV) navigation called On Visible Point Clouds Mesh (OVPC Mesh). Our approach represents the surrounding of the robot as a watertight 3D mesh generated from local point cloud data in order to represent the free […]

Walking Posture Adaptation for Legged Robot Navigation in Confined Spaces Legged robots have the ability to adapt their walking posture to navigate confined spaces due to their high degrees of freedom. However, this has not been exploited in most common multilegged platforms. This paper presents a deformable bounding box abstraction of the robot model, with accompanying mapping and planning strategies, […]

Quantifying the Reality Gap in Robotic Manipulation Tasks We quantify the accuracy of various simulators compared to a real world robotic reaching and interaction task. Simulators are used in robotics to design solutions for real world hardware without the need for physical access. The ‘reality gap’ prevents solutions developed or learnt in simulation from performing well, or at at […]

Local Descriptor for Robust Place Recognition using LiDAR Intensity Place recognition is a challenging problem in mobile robotics, especially in unstructured environments or under viewpoint and illumination changes. Most LiDAR-based methods rely on geometrical features to overcome such challenges, as generally scene geometry is invariant to these changes, but tend to affect camera-based solutions significantly. Compared to cameras, however, LiDARs […]