BotPapers

Sažeci napisanima jednostavnim jezikom najnovijih istraživanja iz robotike — humanoidni roboti, coboti, industrijska automatizacija, dronovi i AI.
232 radovi
A Smarter Way to Build Compact Semantic Maps for Mobile Robots
Roboticsdanas

A Smarter Way to Build Compact Semantic Maps for Mobile Robots

M2-SMap creates compact semantic 3D maps with 18.7% fewer primitives, zero measured object adhesion, and real-time processing.

QiYing Deng, ZhongLai Wang, Yuan Gao, Wei Dong

Robot Transient Contact Detection and Ranging with 6D Dynamic Tactile Sensing
Roboticsdanas

Robot Transient Contact Detection and Ranging with 6D Dynamic Tactile Sensing

However, most existing works rely on dense sensor arrays or high-dimensional visual processing.

Haowen Zheng, Yinghao Wu, Fuyuan Liu +2

Persistent 3D Memory for Cross-Floor Multi-Object Navigation
AIdanas

Persistent 3D Memory for Cross-Floor Multi-Object Navigation

We introduce HM3D-MFMON, comprising 927 three-goal episodes from 36 multi-floor HM3D scenes.

Zehui Li, Zihao Sun, Jiawei Xu +6

Synthetic LiDAR Data and Critical Point Downsampling for Edge Classification
AIjučer

Synthetic LiDAR Data and Critical Point Downsampling for Edge Classification

Niclas Meyer, Stefan Reitmann

OpenArm Mobile Manipulation Through Auditable Robot Representation Handoffs and Skills
AIjučer

OpenArm Mobile Manipulation Through Auditable Robot Representation Handoffs and Skills

Yang Shen, Chonghao Cheng, Ziyi Zhao +6

3D Scene Memory Helps Vision-Language Robots Navigate Closed-Loop Environments
AIjučer

3D Scene Memory Helps Vision-Language Robots Navigate Closed-Loop Environments

WNM-3D adds 3D scene conditioning to vision-language navigation, improving closed-loop performance and action-to-motion consistency.

Yuehao Huang, Yunzi Wu, Xiaotao Zhang +7

TEMPO: Decoupled Reinforcement Learning for Vision-Language-Action Robot Control
Roboticsprekjučer

TEMPO: Decoupled Reinforcement Learning for Vision-Language-Action Robot Control

This paper presented TEMPO, a semantic-action decoupled RL post-training framework for vision-language-action models.

Ziheng Liu, Quantao Yang

Adaptive Gait Timing for Fault-Tolerant Quadruped Locomotion
AIprekjučer

Adaptive Gait Timing for Fault-Tolerant Quadruped Locomotion

Giovanbattista Gravina, Luca Rossini, Carlo Rizzardo +2

Probing and Pruning Planning Tokens in Driving Vision-Language-Action Models
Roboticsprekjučer

Probing and Pruning Planning Tokens in Driving Vision-Language-Action Models

Harisankar Babu, Benjamin Coors, Christopher Lang +3

Hierarchical Post-Training for Reliable Robotic Manipulation
Roboticsprije 3 dana

Hierarchical Post-Training for Reliable Robotic Manipulation

We propose a hierarchical decomposition framework for robotic manipulation control named HiRoC.

He Kong, Zengjue Chen, Qi Wang +6

Adaptive Early-Exit Planning Uses Video-Diffusion Features for Efficient Driving Robots
Roboticsprije 3 dana

Adaptive Early-Exit Planning Uses Video-Diffusion Features for Efficient Driving Robots

On NAVSIM v1, we first use identical fixed-exit, single-trajectory readouts to test sensitivity to video-noise level and DiT depth.

Sining Ang, Yuguang Yang, Yan Wang

Testing Visual Grounding in Zero-Shot Vision-Language Robot Control
AIprije 3 dana

Testing Visual Grounding in Zero-Shot Vision-Language Robot Control

J. de Curtò, Dayani Plasencia, Diego Sánchez +1

Robots Can Cover Unknown Surfaces Using Ergodic Control Instead of Maps
Roboticsprije 4 dana

Robots Can Cover Unknown Surfaces Using Ergodic Control Instead of Maps

Stefan Schneyer, Timo Bachmann, Maged Iskandar +4

Touchscreen Teleoperation Interface for Robotic Manipulator Control
Roboticsprije 4 dana

Touchscreen Teleoperation Interface for Robotic Manipulator Control

A total of 20 participants took part in the study, of whom 17 chose to disclose demographic information.

Juan José García Cárdenas, Alperen Kenan, Hamidreza Raei +4

Learning Human-Like Robot Handwriting from Demonstrations and Force Data
AIprije 4 dana

Learning Human-Like Robot Handwriting from Demonstrations and Force Data

Several datasets have been proposed to study human handwriting and drawing behaviour.

Alperen Kenan, Paul Bremner, Manuel Giuliani

Interactive Visual-Action World Models for Generalizable Robot Manipulation
Roboticsprije 5 dana

Interactive Visual-Action World Models for Generalizable Robot Manipulation

Chenghao Gu, Hanyang Yu, Jingbo Zhang +7

MRI-Safe Master-Slave Robot Enables Remote Needle Guidance in Closed MRI Bores
Roboticsprije 5 dana

MRI-Safe Master-Slave Robot Enables Remote Needle Guidance in Closed MRI Bores

Omar Curiel, Jing-Yuan Huang, Po-Chih Chen +6

One Policy Controls Three Robots Using Shared Skills Across Different Bodies
Roboticsprije 5 dana

One Policy Controls Three Robots Using Shared Skills Across Different Bodies

DyPES-VLA uses future video prediction and robot-specific control heads to operate across three different robot embodiments.

Junfeng Li, Junjie He, Zhide Zhong +12

Semantic Anchored Correspondence for Zero-Shot Robot Skill Transfer
Roboticsprije 6 dana

Semantic Anchored Correspondence for Zero-Shot Robot Skill Transfer

SemAnCorr is a training-free framework establishing dense correspondence across objects by anchoring semantically meaningful regions and propagating constraints via functional maps for zero-shot manipulation skill transfer.

Xiaoxiang Dong, William Baron, Hongyi Chen +3

World Critic Model Boosts Vision-Language-Action Reinforcement Learning
Roboticsprije 6 dana

World Critic Model Boosts Vision-Language-Action Reinforcement Learning

Senyu Fei, Xiaopeng Yu, Siyin Wang +3

🍪 Postavke kolačića

Koristimo kolačiće za mjerenje učinkovitosti. Pravila privatnosti