robots-2

Robot Manipulation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in robot-manipulation-2

Trend

Dataset

Best Model

Actions

RLBench

Libraries

i

Use these libraries to find robot-manipulation-2 models and implementations

nickgkan/3d_diffuser_actor

3 papers 107

Datasets

Subtasks

Robot Manipulation Generalization

Most implemented papers

DeepIM: Deep Iterative Matching for 6D Pose Estimation

D. Fox, Yu Xiang, Xiangyang Ji, Gu Wang, Yi Li•Fri Mar 30 2018

A novel deep neural network for 6D pose matching named DeepIM is proposed, trained to predict a relative pose transformation using a disentangled representation of 3D location and 3D orientation and an iterative training process.

764

Content

stepjam/ARM

2 papers 143

0

Paper Graph

SilhoNet: An RGB Method for 6D Object Pose Estimation

M. Johnson-Roberson, G. Billings•Mon Sep 17 2018

A novel method called SilhoNet is introduced that predicts 6D object pose from monocular images using a convolutional neural network pipeline that takes in region of interest proposals to simultaneously predict an intermediate silhouette representation for objects with an associated occlusion mask and a 3D translation vector.

66 0

Paper Graph

Reinforcement learning for robotic manipulation using simulated locomotion demonstrations

G. Montana, Ozsel Kilinc, Yang Hu•Tue Oct 15 2019

This paper introduces a framework whereby an object locomotion policy is initially obtained using a realistic physics simulator, and this policy is then used to generate auxiliary rewards, called simulated locomotion demonstration rewards (SLDRs), which enable us to learn the robot manipulation policy.

47 0

Paper Graph

Learning 3D Dynamic Scene Representations for Robot Manipulation

Shuran Song, Jiajun Wu, Zhanpeng He, Zhenjia Xu•Mon Nov 02 2020

This paper introduces 3D Dynamic Scene Representation (DSR), a 3D volumetric scene representation that simultaneously discovers, tracks, reconstructs objects, and predicts their dynamics while capturing all three properties, and proposes DSR-Net, which learns to aggregate visual observations over multiple interactions to gradually build and refine DSR.

65 0

Paper Graph

Mobile Robot Manipulation using Pure Object Detection

Brent A. Griffin•Thu Jan 27 2022

This paper develops an end-to-end manipulation method based solely on detection and introduces Task-focused Few-shot Object Detection (TFOD) to learn new objects and settings.

12 0

Paper Graph

What Matters in Language Conditioned Robotic Imitation Learning Over Unstructured Data

Wolfram Burgard, Oier Mees, Lukás Hermann•Tue Apr 12 2022

An extensive study of the most critical challenges in learning language conditioned policies from offline free-form imitation datasets is conducted and a novel approach is presented that significantly outperforms the state of the art on the challenging language conditioned long-horizon robot manipulation CALVIN benchmark.

188 0

Paper Graph

Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

P. Abbeel, Kimin Lee, Xi-Xi Liang, Katherine Shu•Mon May 23 2022

The main idea is to design an intrinsic reward by measuring the novelty based on learned reward by utilizing disagreement across ensemble of learned reward models, which reflects uncertainty in tailored human feedback and could be useful for exploration.

69 0

Paper Graph

Instruction-driven history-aware policies for robotic manipulations

I. Laptev, C. Schmid, Makarand Tapaswi, Shizhe Chen, Pierre-Louis Guhur, Ricardo Garcia Pinel•Sat Sep 10 2022

This work proposes a unified transformer-based approach that takes into account multiple inputs, integrates natural language instructions and multi-view scene observations and improves manipulation precision using multiple views and outperforms the state of the art.

143 0

Paper Graph

VIMA: General Robot Manipulation with Multimodal Prompts

Li Fei-Fei, Linxi (Jim) Fan, Yuke Zhu, Yunfan Jiang, Anima Anandkumar, Guanzhi Wang, Agrim Gupta, Zichen Zhang, Yongqiang Dou, Yanjun Chen•Wed Oct 05 2022

It is shown that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens, and designed a transformer-based robot agent, VIMA, that processes these prompts and outputs motor actions autoregressively.

487 0

Paper Graph

Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation

Zhou Xian, Katerina Fragkiadaki, Théophile Gervet, Nikolaos Gkanatsios•Thu Jun 29 2023

Act3D is introduced, a manipulation policy transformer that represents the robot's workspace using a 3D feature field with adaptive resolutions dependent on the task at hand, and sets a new state-of-the-art in RL-Bench, an established manipulation benchmark.

135 0

Paper Graph

Adding a benchmark result helps the community track progress.