Search Results for author:
Found 32 papers, 11 papers with code
OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data
This work presents OVIR-3D, a straightforward yet effective method for open-vocabulary 3D object instance retrieval without using any 3D data for training.
Ranked #4 on
3D Open-Vocabulary Instance Segmentation
on Replica
Detect Everything with Few Examples
DE-ViT establishes new state-of-the-art results on all benchmarks.
Ranked #1 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Optical Flow boosts Unsupervised Localization and Segmentation
Our fine-tuning procedure outperforms state-of-the-art techniques for unsupervised semantic segmentation through linear probing, without the use of any labeled data.
Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos
This work proposes a self-supervised learning system for segmenting rigid objects in RGB images.
Mono-STAR: Mono-camera Scene-level Tracking and Reconstruction
We present Mono-STAR, the first real-time 3D reconstruction system that simultaneously supports semantic fusion, fast motion tracking, non-rigid object deformation, and topological change under a unified framework.
Scene-level Tracking and Reconstruction without Object Priors
We present the first real-time system capable of tracking and reconstructing, individually, every visible object in a given scene, without any form of prior on the rigidness of the objects, texture existence, or object category.
USHER: Unbiased Sampling for Hindsight Experience Replay
Dealing with sparse rewards is a long-standing challenge in reinforcement learning (RL).
Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations
This work aims to learn how to perform complex robot manipulation tasks that are composed of several, consecutively executed low-level sub-tasks, given as input a few visual demonstrations of the tasks performed by a person.
Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks
Highly constrained manipulation tasks continue to be challenging for autonomous robots as they require high levels of precision, typically less than 1mm, which is often incompatible with what can be achieved by traditional perception systems.
A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs
The triplet examples are finally used to train a siamese neural network that projects the generic visual features into a low-dimensional manifold.
DIPN: Deep Interaction Prediction Network with Application to Clutter Removal
The high accuracy of DIPN allows direct integration with a grasp network, yielding a robotic manipulation system capable of executing challenging clutter removal tasks while being trained in a fully self-supervised manner.
Learning Transition Models with Time-delayed Causal Relations
This paper introduces an algorithm for discovering implicit and delayed causal relations between events observed by a robot at arbitrary times, with the objective of improving data-efficiency and interpretability of model-based reinforcement learning (RL) techniques.
Model-based Reinforcement Learning
reinforcement-learning
+1
Task-driven Perception and Manipulation for Constrained Placement of Unknown Objects
The effectiveness of the proposed approach is demonstrated by developing a robotic system that picks a previously unseen object from a table-top and places it in a constrained space.
Robotics
Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands
Precise in-hand manipulation is an important skill for a robot to perform tasks in human environments.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Learning to Transfer Dynamic Models of Underactuated Soft Robotic Hands
We find that a major cause of these problems is that models trained on small amounts of data can have chaotic or divergent behavior in some regions.
Identifying Mechanical Models through Differentiable Simulations
This paper proposes a new method for manipulating unknown objects through a sequence of non-prehensile actions that displace an object from its initial configuration to a given goal configuration on a flat surface.
Learning to Slide Unknown Objects with Differentiable Physics Simulations
We propose a new technique for pushing an unknown object from an initial configuration to a goal configuration with stability constraints.
Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects
To evaluate this method, a dataset of densely packed objects with challenging setups for state-of-the-art approaches is collected.
Inferring 3D Shapes of Unknown Rigid Objects in Clutter through Inverse Physics Reasoning
We present a probabilistic approach for building, on the fly, 3-D models of unknown objects while being manipulated by a robot.
Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter
This work proposes an autonomous process for pose estimation that spans from data generation to scene-level reasoning and self-learning.
Learning Object Localization and 6D Pose Estimation from Simulation and Weakly Labeled Real Images
We then show that the performance of the detector can be substantially improved by using a small set of weakly annotated real images, where a human provides only a list of objects present in each image without indicating the location of the objects.
Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games
This paper presents a new and efficient method for learning such representations.
Robust 6D Object Pose Estimation with Stochastic Congruent Sets
The pointsets are then matched to congruent sets on the 3D object model to generate pose estimates.
Efficient Model Identification for Tensegrity Locomotion
This paper aims to identify in a practical manner unknown physical parameters, such as mechanical models of actuated robot links, which are critical in dynamical robotic tasks.
Improving 6D Pose Estimation of Objects in Clutter via Physics-aware Monte Carlo Tree Search
Experimental results indicate that this process is able to quickly identify in cluttered scenes physically-consistent object poses that are significantly closer to ground truth compared to poses found by point cloud registration methods.
Fast Model Identification via Physics Engines for Data-Efficient Policy Search
This paper presents a method for identifying mechanical parameters of robots or objects, such as their mass and friction coefficients.
Information-theoretic Model Identification and Policy Search using Physics Engines with Application to Robotic Manipulation
We consider the problem of a robot learning the mechanical properties of objects through physical interaction with the object, and introduce a practical, data-efficient approach for identifying the motion models of these objects.
A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation
The models are placed in physically realistic poses with respect to their environment to generate a labeled synthetic dataset.
Gradient Weights help Nonparametric Regressors
In regression problems over $\real^d$, the unknown function $f$ often varies more in some coordinates than in others.
Algorithms for Learning Markov Field Policies
We present a new graph-based approach for incorporating domain knowledge in reinforcement learning applications.
Bootstrapping Apprenticeship Learning
We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, cover only a small part of a large state space.
