Forschungs-Papers

Allgemeinverständliche Zusammenfassungen der neuesten Robotikforschung – humanoide Roboter, Vierbeiner, industrielle Automatisierung und KI.
499 Papers
Robotic Muscle Memory Accelerates Vision-Language-Action Model Inference
AI17. Sept.

Robotic Muscle Memory Accelerates Vision-Language-Action Model Inference

Despite differences in task objectives, these applications share a common execution pattern: a robot operates at a fixed workstation and repeatedly performs similar tasks.

Kaijun Zhou, Zhiyang Li, Le Chen, Jinyu Gu

Zero-Shot Force-Aware Robot Manipulation Using Generated Video and Audio
AI17. Sept.

Zero-Shot Force-Aware Robot Manipulation Using Generated Video and Audio

We presented a pipeline that jointly uses generated video and audio to construct force-aware trajectories for contact-rich manipulation.

Guanhua Ji, Tianyu Li, Dayoon Suh +3

Hybrid Reachability for Safe Goal-Driven Robot Control
Robotics16. Sept.

Hybrid Reachability for Safe Goal-Driven Robot Control

Hybrid dynamical systems model robotic systems exhibiting continuous and discrete dynamics, but ensuring their safety and performance remains challenging.

Javier Borquez, Shuang Peng, Somil Bansal

Decentralized Gaussian Processes for Spatial Field Estimation with Robot Swarms
Robotics16. Sept.

Decentralized Gaussian Processes for Spatial Field Estimation with Robot Swarms

Guillermo Legarda Herranz, Gianpiero Francesca, Mauro Birattari

Episode-Normalized Conformal Prediction for Reliable Coverage in Vision-and-Language Navigation Policies
AI16. Sept.

Episode-Normalized Conformal Prediction for Reliable Coverage in Vision-and-Language Navigation Policies

Vicky Feliren, A. Taufiq Asyhari, Muhamad Risqi U. Saputra

Learning Adaptive Safety Margins for Visual Navigation
AI15. Sept.

Learning Adaptive Safety Margins for Visual Navigation

Mobile robots are increasingly deployed in human-centric indoor environments such as homes, hospitals, and labs, where success depends not only on geometric …

Junyi Hu, Shuaihang Yuan, Geeta Chandra Raju Bethala +2

Autonomous Racing Defense: How RL-Guided Control Blocks Faster Opponents
Robotics15. Sept.

Autonomous Racing Defense: How RL-Guided Control Blocks Faster Opponents

A new hierarchical framework combines reinforcement learning and model predictive control to give slower autonomous race cars the ability to fend off faster …

Yufei Xi, Yijie Liao, Tulga Ersal

Real-Time Traffic Management for Heterogeneous AGVs in Narrow Industrial Environments
Industrial15. Sept.

Real-Time Traffic Management for Heterogeneous AGVs in Narrow Industrial Environments

Alessandro Bonetti, Silvia Proia, Simone Guidetti +1

Distributed Model-Based Diffusion for Scalable Multi-Robot Trajectory Planning
Robotics14. Sept.

Distributed Model-Based Diffusion for Scalable Multi-Robot Trajectory Planning

Haejoon Lee, Xinyi Wang, Taekyung Kim +1

Safer Robot Skill Adaptation Around Moving Obstacles
Robotics14. Sept.

Safer Robot Skill Adaptation Around Moving Obstacles

Dist-GPRL helps robots adapt demonstrated manipulation skills around moving obstacles while preserving smooth motion and reducing collisions.

A K M Nadimul Haque, Sheila Sutjipto, Marc G. Carmichael +1

CARLAverse: Modular Multimodal Human-in-the-Loop Simulation Framework
Robotics14. Sept.

CARLAverse: Modular Multimodal Human-in-the-Loop Simulation Framework

This section reviews existing approaches in hardware abstraction, the current state of mixed-traffic simulation, and technical challenges in distributed physics.

Patrick Rebling, Philipp Nenninger, Reiner Kriesten

Touch-Enhanced Robot Learning Boosts Precision Tasks by Combining Sight and Feel
Robotics13. Sept.

Touch-Enhanced Robot Learning Boosts Precision Tasks by Combining Sight and Feel

Ning Cheng, Jinan Xu, Wanlin Li +5

KAI: Kinematic Interface Boosts Robot Manipulation with Less Data
Robotics13. Sept.

KAI: Kinematic Interface Boosts Robot Manipulation with Less Data

Yaping Li, Zhaxizhuoma, Qiaojun Yu +3

Memory-Grounded Planning for Efficient Long-Horizon Robotic Manipulation Tasks
Robotics13. Sept.

Memory-Grounded Planning for Efficient Long-Horizon Robotic Manipulation Tasks

In memory-dependent tasks, long-horizon visual history is not necessarily required as a direct input to the execution model at every control step.

Sizhe Zhao, Haozhe Xie, Weiyu Zhao +5

Motion-Consistent Detection and Socially-Aware Trajectory Forecasting
Robotics12. Sept.

Motion-Consistent Detection and Socially-Aware Trajectory Forecasting

Two obstacles motivate this paper: DeTra has no public implementation, and forecasting dynamic actors remains markedly harder than detection.

Vladislav Diuzhev, Dmitry Yudin

How Organizational Principles Improve Collective Intelligence in Embodied AI Teams
AI12. Sept.

How Organizational Principles Improve Collective Intelligence in Embodied AI Teams

Zhengran Ji, Jonathan Hyun, Boyuan Chen

Shared Exoskeleton Enables One-to-One Dexterous Robot Demonstrations
Robotics12. Sept.

Shared Exoskeleton Enables One-to-One Dexterous Robot Demonstrations

Tengbo Yu, Jiahao Wu, Daohan Li +4

Robotics11. Sept.

Dynamic Semantic Mapping Helps Robots Understand Changing Spaces in Real Time

A hybrid semantic mapping pipeline combines camera geometry, object tracking, regression correction, and ontologies for live robot world models.

Konstantinos Dimitropoulos, Ioannis Hatzilygeroudis

Rapid Learning Enables Dexterous In-Hand Pen Writing with Real-Time Jacobian Estimation
Robotics11. Sept.

Rapid Learning Enables Dexterous In-Hand Pen Writing with Real-Time Jacobian Estimation

Uncalibrated visual servoing learns the differential map between sensed features and actuation online, with no camera or kinematic calibration.

Kai Stewart, Yasunori Toshimitsu, Robert K. Katzschmann

Learning Agent-Based MPC Helps Vehicles Coordinate Unknown Controllers in Real Time
Robotics11. Sept.

Learning Agent-Based MPC Helps Vehicles Coordinate Unknown Controllers in Real Time

Jiaming Zhong, Reza Valiollahi Mehrizi, Mohammad Pirani +4