Robotics: research

Journal articles, academic blogs, think-tank reports and papers in this section, newest first. Back to the news.

arXiv (research papers) Qinfeng Zhu

LEASH: Stay Safe in Agentic Robotics

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to control robots poses serious safety risks, and comprehensive safety evaluation is still lacking. We introduce RoboRisk, a comprehensive benchmark for evaluating safety in agentic robotics. Its 92…

Read at arXiv (research papers)

arXiv (research papers) Dimitris Panagopoulos

Model-Free Runtime Measurement of Task-Relevant Information

Autonomous systems increasingly monitor physical kinematics, environmental states and task completion outcomes. While existing work provides methods to plan information seeking actions and interpret acquired observations, current approaches do not monitor whether the live process of information gathering is functioning properly. Consequently, such systems can remain operationally active without resolving outstanding mission requirements. To address this limitation, we…

Read at arXiv (research papers)

arXiv (research papers) Huaijin Pi

DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning

We study how to generate diverse, physically executable robot demonstrations for dexterous vision-language-action (VLA) learning. Existing demonstration-generation methods typically rely on costly teleoperated examples. Meanwhile, human hand--object datasets provide a reusable source, but existing transfer methods mainly reproduce given interactions. Turning these interactions into VLA training data further requires coverage of different objects and manipulation locations…

Read at arXiv (research papers)

arXiv (research papers) Jinhua Chen

A human-in-the-loop Control Paradigm for Construction Robotics: From VR-Guided Teleoperation to Semi-Autonomous Dual-Arm Operation

Construction tasks in hazardous and unstructured environments require both human adaptability and robotic precision, yet existing approaches often treat teleoperation and autonomy as separate control modes. This paper presents a human-in-the-loop control paradigm that enables structured transitions among VR-guided teleoperation, semi-autonomous shared control, and rule-based autonomous execution for contact-rich dual-arm construction tasks. The proposed system combines…

Read at arXiv (research papers)

arXiv (research papers) Zepeng Wang

RedirectMimic: Local Motion Content Redaction for Humanoid Whole-Body Control

Humanoid motion interfaces should accommodate application-specific movement constraints while retaining useful reference behavior. Local content redaction requires a controller to replace selected movements even when it continues to receive the original reference. Removing the tracking incentive for those movements leaves their replacement unspecified. We introduce RedirectMimic, which separates the reference observed by the actor from the target used to train its execution…

Read at arXiv (research papers)

arXiv (research papers) Xuheng Zhang

LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning

World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation, endowing policies with strong capabilities for modeling temporal and physical dynamics. Existing WAMs, encompassing both video-first action prediction and joint video-action modeling, directly transfer global physical representations from world models to action generation. However, global scene representations may underemphasize local robot-object interactions, creating a…

Read at arXiv (research papers)

arXiv (research papers) Haiyang Wu

HiPFuse: Real-Time LiDAR Semantic Segmentation for Robotic Perception on Edge Devices

Real-time robotic perception requires accurate LiDAR semantics under limited resources. Bird's-eye-view (BEV) aggregation is efficient but can mix differently labeled surfaces in columns. We present HiPFuse, a point-BEV fusion framework that exchanges point and height-partitioned BEV features across horizontal scales, combining point-wise detail with 2D spatial context from one LiDAR scan. Fixed height assignments preserve separate vertical aggregation groups, with auxiliary…

Read at arXiv (research papers)

arXiv (research papers) Shiva Ganesh Murali

Optimization-Based Path Planning for Industrial Manipulators: Experimental Validation in Additive Manufacturing

Robotic additive manufacturing requires joint paths that reconcile robot feasibility with process-specific geometry. We develop an offline optimization-based path planner that combines joint-path regularity and self-collision penalties with process costs and constraints, so that a new process enters through its own reference, residuals, and tolerances. Full-path and boundary-coupled chunked optimization handle references of different lengths. Iterative Weight Tuning (IWT)…

Read at arXiv (research papers)

arXiv (research papers) Niran Nataraj SI

TransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic Microsurgery

Intraoperative scene perception in ophthalmic microsurgery is limited by instrument occlusion: when a tool enters the high-magnification field, it conceals tissue from both the surgeon and the perception components of robot-assisted systems that process the video. Generative inpainting can remove the occluder but replaces the missing image content with synthesis, which is unsuitable when visual provenance matters. Many video inpainters also depend on future frames and cannot…

Read at arXiv (research papers)

arXiv (research papers) Xianghui Wang

ReACT: Reflection-Consistent Modulation and Cross-Load Consistency for Humanoid Velocity Tracking Under Asymmetric Loads

In recent years, humanoid loco-manipulation has progressed to whole-body grasping, lifting, and transport. A basic requirement underlying these tasks is carrying the object to its destination, which depends on the locomotion controller accurately executing velocity commands from the navigation policy. However, carrying an object in one hand introduces a persistent asymmetric upper-body load that can degrade velocity tracking. Persistent tracking biases can accumulate into…

Read at arXiv (research papers)

arXiv (research papers) Kim Alexander Christensen

Persistent Metric-Semantic Maritime Scene Memory from Open-Vocabulary 3D Scene Graphs

Three-dimensional scene graphs (3DSGs) can provide robots with persistent metric-semantic representations for spatial reasoning, but the existing methods have primarily been developed for indoor and terrestrial environments. In this paper we investigate how a representative outdoor open-vocabulary method transfers to maritime environments and which adaptations are needed. Our experiments show that zero-shot representative outdoor 3DSG descriptions agree with our labeled…

Read at arXiv (research papers)

arXiv (research papers) Eduardo Figueiredo

Learn-To-Propagate: Distributionally Robust Motion Planning for Nonlinear Uncertain Systems

Motion planning for stochastic systems aims to find a sequence of control inputs that drives a system to a goal set while avoiding unsafe states with high probability. Existing approaches, however, are either restricted to linear dynamics with perfect knowledge of the underlying distributions or lack formal correctness guarantees. To address these limitations, we propose \emph{Learn-To-Propagate Distributionally-Robust Forest (L2P-DR-Forest)}, a distributionally-robust…

Read at arXiv (research papers)

arXiv (research papers) Bastien Dussard LAAS-RIS, LAAS

Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics

While symbolic reasoning for task allocation requires grounding a robot's physical capabilities, standard Unified Robot Description Format (URDF) files provide only low-level kinematics without the formal semantic context needed for reasoning. We present URDF2Ontology, an automated, taxonomy-agnostic neurosymbolic framework that transforms raw URDF files into populated, grounded OWL ontologies. It leverages a Large Language Model (LLM) for targeted semantic reasoning…

Read at arXiv (research papers)

Google DeepMind blog SI

Gemini Robotics 2.5 accelerates real-world general dexterity

Our most capable vision-language-action model enhances robot dexterity, reliability, and safety

Read at Google DeepMind blog

arXiv (research papers) Xinrui Zu SI

$Σ$-LeWM: Learning World Models via S-Information for Robot Control

World models have increasingly been applied as a model-based control method for robotics tasks such as manipulation and locomotion. While early world model architectures relied on decoders to prevent mode collapse and learn a predictable latent space, recent works on world models, such as Joint Embedding Predictive Architecture or LeWorldModel, increasingly aim to learn embeddings without a grounding decoder, utilising only a latent forward dynamics predictor and a…

Read at arXiv (research papers)

MIT News AI Jennifer Chu | MIT News SI

AI-assisted learning platform helps robots reason beyond literal commands

The new approach, known as FLEX, could lead to more intuitive, interactive household and assistive robots.

Read at MIT News AI

Journal articles (OpenAlex) Xiaohan Liu, Ziwu Ren, Yunxi Miao et al. · International Journal of Robust and Nonlinear Control

Sliding Mode Controller Design for Robotic Manipulator Based on the Hybrid Pigeon‐Inspired Optimization

ABSTRACT To address the challenge of finding the optimal parameter combination for proportional–integral sliding mode (PISM) controllers in robotic manipulators, this article proposes a novel hybrid pigeon‐inspired optimization (HPIO) algorithm for systematic parameter tuning. The proposed algorithm enhances the conventional PIO framework by incorporating a predation‐inspired random perturbation mechanism and a dynamic population screening strategy, thereby balancing global…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Bartosz Bieńkowski, Wojciech Kaczmarek · Sensors

Recognition, Stabilization, and Command-Mapping Algorithms for Contactless Hand-Gesture Control of an ABB Industrial Robot

Although contactless hand-gesture interfaces can support intuitive human–robot interaction, transient classification errors may trigger unintended commands when classifier outputs are mapped directly to robot actions. This study presents a processing framework for contactless control of an ABB IRB 120 industrial robot. The framework combines RGB acquisition, geometric normalization of 21 MediaPipe hand landmarks, population-based sample filtering, multilayer perceptron…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Manuel J Heredia-Rios, Enrique Pérez‐Gutiérrez, Francisco Domingo Calvo López et al. · The International Journal of Advanced Manufacturing Technology

Integration of an ABB YuMi collaborative robot and a CNC doctor-blade coater into an event-driven cyber-physical manufacturing workcell

Abstract This work presents an event-driven cyber-physical manufacturing workcell that integrates an ABB YuMi collaborative robot with a computer numerical control (CNC) doctor-blade coater for laboratory-scale thin-film processing. Both subsystems retain their local motion-control routines, while Node-RED acts as the supervisory layer and coordinates process progression through high-level commands and reported execution states. Communication is implemented through a hybrid…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Changjian Wang, Zhang Tianyou · Frontiers in Psychology

Empirical study on how lower limb exoskeleton robots improve older adults’ physical performance through psychological mechanisms

Objective This study aims to explore how lower limb exoskeleton robots enhance physical performance in older adults and clarify the mediating role of psychological factors during human-robot interaction exercises. Methods The study focused on healthy older adults in the community and used a randomized controlled trial design along with qualitative research methods. A total of 60 participants aged 60–75 were selected and divided into an lower limb exoskeleton robots…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Raveeroj Bawornkitchaikul, Ruikang K. Wang, Matthew O’Donnell et al. · Biomedical Optics Express

DINOCT: robust skin surface localization for robotic noncontact dynamic optical coherence elastography

Noncontact dynamic optical coherence elastography (OCE) can measure the elastic properties of anterior soft tissues. However, applying OCE to skin requires tracking mechanical waves propagating in multiple directions to reconstruct mechanical anisotropy. Robotic scanning is well suited to this task but requires accurate probe positioning, alignment to the surface normal, and precise, repeatable rotation. To ensure phase and polarization stability, polarization-maintaining…

Read at Journal articles (OpenAlex)

arXiv (research papers) Hongyu Luo

Compute Regeneration through Re-Productization: Reorganizing Retired Edge AI Silicon into a Delivered Multilingual Service Robot

Useful edge hardware can lose product support while retaining substantial computation. We treat this as systems design: compute regeneration here means re-productization, retaining the compute module while redesigning the surrounding product organization. Our case is GEdgeBot, a multilingual service robot built around a retired 32 GB Jetson AGX Xavier. A source-grounded inventory shows the box alone supplies inference, while the combined system exposes five on-device AI…

Read at arXiv (research papers)

arXiv (research papers) Zhengyang Cheng

Efficient VLA Inference via Retrieval-Based Speculation and Hardware Acceleration

Vision-language-action (VLA) models enable robots to understand and execute complex instructions, but their autoregressive (AR) action generation introduces significant latency on resource-constrained robotic platforms. Speculative decoding can accelerate AR-based inference by parallelizing action generation and verification; however, existing approaches rely on costly draft models, which are inefficient on edge platforms. In this paper, we propose Zora, a hardware-software…

Read at arXiv (research papers)

Journal articles (OpenAlex) Minyang Wang, Bangcheng Zhang, Zhi Wei Gao · Mathematics

An Uncertainty-Adaptive Robust Graph-Based Belief Rule Base for Interpretable Four-State Fault Diagnosis of Industrial Robots

Industrial robot severity diagnosis must combine evidence from coupled subsystems while remaining stable under fluctuating measurements. We develop an uncertainty-adaptive robust graph-based belief rule base (RG-BRB) that maps monitored attributes to transmission, servo-control, and motion-execution nodes. A row-stochastic graph propagates node evidence, while local fluctuation adjusts antecedent widths and attribute reliability before rule activation. Normalized evidential…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Shih‐Hao Chang, Minyechil Alehegn Tefera, Jun-Ming Cheng et al. · Sensors

Vision-Guided Robotic Arm with Deep Learning and Secure Digital Twin for Pre-Deployment Quadruped Robot Operation

In this article, we propose a vision-guided robotic arm system that integrates deep learning, digital twin, and cybersecurity to enhance the maintenance of quadruped robots. The proposed system comprises two core components. (1) A YOLOv11-based object detection system with depth cameras identifies maintenance targets and extracts 3D coordinates for autonomous robotic arm localization and manipulation. (2) A digital twin environment is used to simulate and validate path…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Minsu Kim, Hoyeon Cho, Sungkeun Yoo et al. · Sensors

Magic-Formula-Based Feedforward Velocity Control of a Magnetically Coupled Wall-Climbing Robot

This study presents a model-based feedforward method for reducing velocity errors during the vertical travel of a magnetically coupled wall-climbing robot. Permanent magnets on opposite sides of the wall maintain magnetic coupling, while a spring-preloaded linkage adjusts the drive-wheel normal force. A dedicated test bench was used to measure the traction–slip characteristics of the urethane roller–acrylic contact at normal forces of 20 and 30 N. Magic Formula models were…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Siqi Sun, Hualong Yu, Boyin Jin et al. · Machines

PC-MAPPO: Phase-Conditioned Rollout Buffering for Multi-Robot Collaborative Motion Planning

Phase-dependent experience creates a practical tension between formation maintenance and obstacle-aware navigation in multi-robot motion planning. This paper presents PC-MAPPO, a phase-conditioned rollout framework for multi-robot formation and obstacle-aware navigation in the evaluated simulation setting. The method retains the Multi-Agent Proximal Policy Optimization (MAPPO) optimizer and reorganizes on-policy data through separate formation and navigation buffers…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Hao Yun-gang, Qi-Xin Zhu, Peng Chen et al. · Actuators

Rigid–Flexible Coupling Design and Variable Stiffness Control of Drive Mechanism Components for Ostrich-Inspired Robots

Ostriches are the fastest bipedal terrestrial animals. Their hip, knee, and ankle joints possess inherent shock-absorbing capabilities, endowing their legs with excellent compliance. This biomechanical feature ensures both stability and high energy efficiency during high-speed locomotion. For ostrich-inspired robots, designing the leg drive mechanism and implementing compliance control are crucial for achieving biomimetic locomotion. Therefore, this study focuses on the knee…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Mohammad Anas Thohir, Nurul Istiq’faroh, Awaluddin Hidayat Ramli Inaku et al. · Eurasia Journal of Mathematics Science and Technology Education

Mapping educational robotics competencies for pre-service teachers in science course: An exploratory sequential mixed-methods study

Educational robotics is increasingly used to develop pre-service elementary teachers’ computational thinking (CT), yet limited empirical evidence exists on the competencies required for robotics-integrated teaching. This exploratory sequential mixed-methods study identified robotics-related perceived competencies and examined the relationships among CT, technological pedagogical content knowledge (TPACK), and robotics pedagogical content knowledge (RPCK). Qualitative data…

Read at Journal articles (OpenAlex)

Older stories