Related papers: Evaluating Robustness of Visual Representations fo…

It is challenging for humans -- particularly those living with physical disabilities -- to control high-dimensional, dexterous robots. Prior work explores learning embedding functions that map a human's low-dimensional inputs (e.g., via a…

In this work, we interpret the representations of multi-object scenes in vision encoders through the lens of structured representations. Structured representations allow modeling of individual objects distinctly and their flexible use based…

This paper investigates robotic peg-in-hole assembly using the Elementary Dynamic Actions (EDA) framework, which models contact-rich tasks through a combination of submovements, oscillations, and mechanical impedance. Rather than focusing…

The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations.…

We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…

We propose a framework enabling mobile manipulators to reliably complete pick-and-place tasks for assembling structures from construction blocks. The picking uses an eye-in-hand visual servoing controller for object tracking with Control…

Robust task-oriented grasp planning is vital for autonomous robotic precision assembly tasks. Knowledge of the objects' geometry and preconditions of the target task should be incorporated when determining the proper grasp to execute.…

Robotic peg-in-hole assembly remains a challenging task due to its high accuracy demand. Previous work tends to simplify the problem by restricting the degree of freedom of the end-effector, or limiting the distance between the target and…

One of the challenges of full autonomy is to have a robot capable of manipulating its current environment to achieve another environment configuration. This paper is a step towards this challenge, focusing on the visual understanding of the…

Standard Vision Transformers flatten 2D images into 1D sequences, disrupting the natural spatial topology. While Rotary Positional Embedding (RoPE) excels in 1D, it inherits this limitation, often treating spatially distant patches (e.g.,…

A fundamental cognitive process is the ability to map value and identity onto objects as we learn about them. Exactly how such mental constructs emerge and what kind of space best embeds this mapping remains incompletely understood. Here we…

Shape assembly, the process of combining parts into a complete whole, is a crucial robotic skill with broad real-world applications. Among various assembly tasks, geometric assembly--where broken parts are reassembled into their original…

Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly focus on policy design, they often neglect the structure and capacity of visual encoders, limiting…

We introduce a new approach for robotic manipulation tasks in human settings that necessitates understanding the 3D geometric connections between a pair of objects. Conventional end-to-end training approaches, which convert pixel…

A large number of studies analyse object detection and pose estimation at visual level in 2D, discussing the effects of challenges such as occlusion, clutter, texture, etc., on the performances of the methods, which work in the context of…

Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques.…

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling high-dimensional RGB representations into control-relevant geometry without overfitting.…

In applications of deep reinforcement learning to robotics, it is often the case that we want to learn pose invariant policies: policies that are invariant to changes in the position and orientation of objects in the world. For example,…

Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over…