Denoising diffusion models have enabled high-quality image generation an...
The success of a multi-kilometre drive by a solar-powered rover at the l...
Quickly and reliably finding accurate inverse kinematics (IK) solutions
...
The small size, high dexterity, and intrinsic compliance of continuum ro...
Following four successful years in the SAE AutoDrive Challenge Series I,...
Advances in lidar technology have made the collection of 3D point clouds...
The popularity of Neural Radiance Fields (NeRFs) for view synthesis has ...
To operate safely and efficiently alongside human workers, collaborative...
Correct radar data fusion depends on knowledge of the spatial transform
...
Reducing the quantity of annotations required for supervised training is...
Adversarial imitation learning (AIL) has become a popular alternative to...
Neural Radiance Fields (NeRFs) have emerged as a popular approach for no...
Reducing the quantity of annotations required for supervised training is...
Autonomous vehicles (AVs) often depend on multiple sensors and sensing
m...
Quickly and reliably finding accurate inverse kinematics (IK) solutions
...
Obtaining 3D object representations is important for creating photo-real...
Sequential modelling of high-dimensional data is an important problem th...
Traditionally, visual-inertial-odometry (VIO) systems rely on filtering ...
Collaborative robots (cobots) are machines designed to work safely along...
The ability to perceive object slip via tactile feedback enables humans ...
Effective exploration continues to be a significant challenge that preve...
Ideally, robots should move in ways that maximize the knowledge gained a...
Inverse kinematics (IK) is the problem of finding robot joint configurat...
Solving the inverse kinematics problem is a fundamental challenge in mot...
Much recent literature has formulated structure-from-motion (SfM) as a
s...
We examine the problem of time delay estimation, or temporal calibration...
Learned visuomotor policies have shown considerable success as an altern...
The ability to perceive object slip through tactile feedback allows huma...
Reliable operation in inclement weather is essential to the deployment o...
Articulated robots such as manipulators increasingly must operate in
unc...
Successful visual navigation depends upon capturing images that contain
...
The majority of inverse kinematics (IK) algorithms search for solutions ...
Building trustworthy autonomous systems is challenging for many reasons
...
Many public sources of cyber threat and vulnerability information exist ...
The self-supervised loss formulation for jointly training depth and egom...
Learning or identifying dynamics from a sequence of high-dimensional
obs...
Supervised imitation learning, also known as behavior cloning, suffers f...
Accurate rotation estimation is at the heart of robot perception tasks s...
Correct fusion of data from two sensors is not possible without an accur...
Cyber security adversaries and engagements are ubiquitous and ceaseless....
We present a self-supervised deep pose correction (DPC) network that app...
We present two novel techniques for detecting zero-velocity events to im...
Inverse kinematics is a fundamental problem for articulated robots: fast...
A significant challenge in manipulation motion planning is to ensure agi...
Estimating unknown rotations from noisy measurements is an important ste...
Accurate estimates of rotation are crucial to vision-based motion estima...
Long-term metric localization is an essential capability of autonomous m...
In this paper, we introduce the Hummingbird: the first completely open-s...
We present a certifiably globally optimal algorithm for determining the
...
We present a method to improve the accuracy of a zero-velocity-aided ine...