activity
20172022
most citedLarge-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

53 citations · 71 across the 3 of their papers we have counts for

collaborators

10 papers

cs.RO202216 cited

Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation

Chia-Man Hung, Shaohong Zhong, Walter Goodwin +4

We present a novel approach to path planning for robotic manipulators, in which paths are produced via iterative optimisation in the latent space of a generative model of robot pos…

cs.LG20212 cited

Universal Approximation of Functions on Sets

Edward Wagstaff, Fabian B. Fuchs, Martin Engelcke +2

Modelling functions of sets, or equivalently, permutation-invariant functions, is a long-standing challenge in machine learning. Deep Sets is a popular method which is known to be…

cs.RO2021

APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation

Yizhe Wu, Oiwi Parker Jones, Martin Engelcke +1

Recent advances in unsupervised learning for object detection, segmentation, and tracking hold significant promise for applications in robotics. A common approach is to frame these…

cs.LG2020

Reconstruction Bottlenecks in Object-Centric Generative Models

Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted t…

cs.RO2020

First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion

Alexander L. Mitchell, Martin Engelcke, Oiwi Parker Jones +5

Traditional approaches to quadruped control frequently employ simplified, hand-derived models. This significantly reduces the capability of the robot since its effective kinematic…

cs.CV2020

RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces

Sebastien Ehrhardt, Oliver Groth, Aron Monszpart +4

We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects. Similar to other generative approaches, RELATE is trained…