Related papers: A Primer on SO(3) Action Representations in Deep R…
Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely…
Graph Neural Networks (GNN) can capture the geometric properties of neural representations in EEG data. Here we utilise those to study how reinforcement-based motor learning affects neural activity patterns during motor planning, leveraging…
Reinforcement learning (RL) for robot control typically requires a detailed representation of the environment state, including information about task-relevant objects not directly measurable. Keypoint detectors, such as spatial autoencoders…
Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data. Rotation, as an important quantity…
We present a semantically rich graph representation for indoor robotic navigation. Our graph representation encodes: semantic locations such as offices or corridors as nodes, and navigational behaviors such as enter office or cross a…
Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities that impede the training of deep learning networks for pose estimation are rarely discussed in the literature. To cope with these…
Humans inherently possess generalizable visual representations that empower them to efficiently explore and interact with the environments in manipulation tasks. We advocate that such a representation automatically arises from…
Reliable watermarking of panoramic imagery is fundamentally challenged by arbitrary 3D rotations. As panoramas are defined on the sphere, they naturally transform under the action of $SO(3)$, rendering conventional planar representations…
Surface manipulation tasks require robots to generate trajectories that comprehensively cover complex 3D surfaces while maintaining precise end-effector poses. Existing ergodic trajectory optimization (TO) methods demonstrate success in…
Robotics policies are always subjected to complex, second order dynamics that entangle their actions with resulting states. In reinforcement learning (RL) contexts, policies have the burden of deciphering these complicated interactions over…
3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art…
Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. It is known that variations in input domains (e.g., different panorama colors due to seasonal changes) or task…
In actor-critic-based reinforcement learning algorithms such as Twin Delayed Deep Deterministic policy gradient (TD3), insufficient exploration of the spatial space can result in suboptimal policies when controlling 7-DOF robotic arms. To…
Non-Euclidean data is frequently encountered across different fields, yet there is limited literature that addresses the fundamental challenge of training neural networks with manifold representations as outputs. We introduce the trick…
We introduce a rotation-invariant representation of planar shapes. In particular, this representation encodes shapes as vectors such that the Euclidean distance between them serves as a valid shape distance. For standardized, star-shaped…
This technical note aims to introduce geometric controllers to roboticists for aligning \emph{3D robots} with non-constant 3D vector fields. This alignment entails the control of the robot's 3D attitude. We derive with excessive detail all…
Developing generalizable robot policies that can robustly handle varied environmental conditions and object instances remains a fundamental challenge in robot learning. While considerable efforts have focused on collecting large robot…
Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw…
The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling…
How to effectively represent camera pose is an essential problem in 3D computer vision, especially in tasks such as camera pose regression and novel view synthesis. Traditionally, 3D position of the camera is represented by Cartesian…