arXivSub Start free trial

IROS 2024 Papers — Page 5

IEEE/RSJ International Conference on Intelligent Robots and Systems · 1581 papers

Design and Development of a Work Cell with a One-Handed Soldering Tool for Enhanced Human-Robot Collaboration

Natchanon Suppaadirek, T. Shibata

Pose EstimationDepth EstimationRobotic IntelligenceImage

🎯 What it does: Designed and developed a work unit tailored for single-arm users, integrating a one-handed welding tool with a robotic arm. The system utilizes depth cameras, machine learning, and Mediapipe human tracking to interpret human intent, enhancing the intuitiveness and effectiveness of human-robot collaboration.

Design and Evaluation of a Prototype Tactile Scanner for Active Sensing of Proximal Objects

A. Dechaux, G. Ganesh

Robotic Intelligence

🎯 What it does: Designed and evaluated a tactile scanner prototype for active perception of nearby objects.

Design and implementation of a novel wheel-based cable inspection robot

Mengqi Hou, Lezhi Hu

Robotic Intelligence

🎯 What it does: Proposed and implemented a novel wheeled cable inspection robot, with detailed elaboration of its structural design, control system, and mechanical analysis of the suspension mechanism, and verified its performance through prototype testing.

Design and Modeling of a Thin-walled Multi-segment Continuum Robotic Bronchoscope

Guibin Bian, Zhen Li

Robotic IntelligenceBiomedical Data

🎯 What it does: Designed and verified a thin-walled multi-segment continuously driven bronchoscope robot system, achieving over 190° of bending and realizing error compensation through a real-time kinematic model, constructing a prototype and validating its functionality in vivo in pigs.

Design and Preliminary Validation of A Multi-mode Quadrotor Aerial-Aquatic Vehicle with Tilting Mechanism

Mengyao Liu, Yayi Shen

Robotic Intelligence

🎯 What it does: Developed a multi-modal quadrotor drone prototype capable of moving in both air and water, and verified its feasibility through experiments.

Design and Validation of Flexible Aerial Robotics for Safe Human-Robot Interaction

Fuhua Jia, Salman Ijaz

Safty and PrivacyRobotic Intelligence

🎯 What it does: Designed and verified a flexible pneumatic robot (SFAR) for safe human-robot and drone interaction

Design Improvements to the Float Upper-Limb Exoskeleton Better Mimics the Glenohumeral Complex Kinematics

Giulia Bodo, Matteo Laffranchi

Robotic Intelligence

🎯 What it does: Design improvements are made for the shoulder and wrist joints of the Float-type upper limb exoskeleton, adopting a 3-DOF RPY wrist architecture and introducing a multi-index evaluation method to verify the enhancement of reachable workspace and the internal/external rotation of the shoulder joint.

Design of a Fully Actuated Drone with Non-Isotropic Wrench Shape

Seongsu Park, Min Jun Kim

OptimizationRobotic Intelligence

🎯 What it does: Proposes a design framework for a fully actuated drone with anisotropic torque shapes to improve energy efficiency during aerial contact operations.

Design of a Multi-robot Coordination System based on Functional Expressions using Large Language Models

Yuki Kato, H. Asama

Robotic IntelligenceTransformerLarge Language ModelVision Language ModelTextMultimodality

🎯 What it does: Proposed a multi-robot coordination system workflow based on large language models (GPT-4, GPT-4V), leveraging functional expression and environmental understanding to achieve adaptive coordination in unknown environments;

Design of a Pneumatically Driven 3D-Printed Under-Actuated Soft Robot with Programmable Stiffness

Zaid Mustafa, Melih Türkseven

Robotic Intelligence

🎯 What it does: Proposed a soft pneumatic actuated 3D printed soft robot using programmable stiffness poly(lactic acid) (PLA) components and embedded heating lines to achieve adjustable stiffness;

Design of a Soft Shell for a Spherical Exploration Robot Traversing Varying Terrain

M. P. Dravid, Robert O. Ambrose

Robotic Intelligence

🎯 What it does: Proposed and constructed a spherical exploration robot with a soft shell, and conducted performance analysis by adjusting the shell pressure to adapt to different terrains.

Design of a Variable Wheel-propeller Integrated Mechanism for Amphibious Robots

Liang Lu, Bin Han

OptimizationRobotic Intelligence

🎯 What it does: A variable wheel blade integration mechanism was proposed, a kinematic model of the blade was established, and multi-objective structural parameter optimization was conducted for ground obstacle crossing and underwater propulsion performance. Finally, a virtual simulation prototype was constructed and its performance was evaluated.

Design of Stickbug: a Six-Armed Precision Pollination Robot

Trevor Smith, Yu Gu

Robotic IntelligenceImageAgriculture Related

🎯 What it does: Designed and implemented a six-armed multi-agent precision pollination robot named Stickbug, capable of combining the precision of single agents with group parallelization to achieve pollination in greenhouse environments;

Design of Upper-Limb Exoskeleton with Distal Branching Link Mechanism for Bilateral Operation of Humanoid Robots

Hiroki Yoshioka, Masayuki Inaba

Robotic Intelligence

🎯 What it does: Designed an upper limb exoskeleton with a distal branch linkage mechanism for bidirectional human-robot operation in humanoid robots.

Design, Modelling, and Experimental Validation of a Soft Continuum Wrist Section Developed for a Prosthetic Hand

S. Sulaiman, F. Ficuciello

Robotic IntelligencePhysics RelatedOrdinary Differential Equation

🎯 What it does: Designed, modeled, and experimentally validated a soft continuous wrist joint for prosthetic arms;

Design, Prototype, and Performance Assessment of an Autonomous Manipulation System for Mars Sample Recovery Helicopter

A. Kalantari, Ryan Mccormick

Robotic IntelligenceImage

🎯 What it does: Designed, prototyped, and tested a ~150g operating system enabling a Mars sample recovery helicopter to autonomously pick up, store, and release recoverable sample tubes and glove assembly (RGA) on the Martian surface.

Det-Recon-Reg: An Intelligent Framework Towards Automated Large-Scale Infrastructure Inspection

Guidong Yang, Ben M. Chen

Object DetectionAnomaly DetectionImagePoint Cloud

🎯 What it does: Propose the Det-Recon-Reg framework, which separates detection, reconstruction, and registration into three stages, achieving automated detection and localization of large-scale infrastructure defects.

Development and Functional Evaluation of The PrHand V3 Soft-Robotics Prosthetic Hand

Orion Ramos, Carlos A. Cifuentes

Robotic Intelligence

🎯 What it does: Studied and evaluated the PrHand V3 soft robotic prosthetic hand, including mechanical improvements and functional assessment.

Development Force Control of a Series Elastic Actuator to Excavator for Mechanization of Manual Work *

Toshifumi Hiramatsu, Hisashi Sugiura

OptimizationRobotic Intelligence

🎯 What it does: Proposed and implemented a force-controlled excavator using series elastic actuators (SEA) to replace traditional hydraulic systems, achieving precise control of the excavator's operational force.

Development of a Bendable and Extendable Soft Gripper Driven by Differential Worm Gear Mechanism

Moses Gladson Selvamuthu, R. Tadakuma

Robotic Intelligence

🎯 What it does: Developed a flexible, stretchable soft gripper that uses a differential worm gear mechanism to drive flexible dual-tooth lever finger tips, which can adjust the length of the fingertips according to the grasped object.

Development of a Bilateral Control Teleoperation System for Bipedal Humanoid Robot Utilizing Foot Sole Haptics Feedback *

Yang Shen, T. Otani

Robotic Intelligence

🎯 What it does: This study develops and verifies a bidirectional control remote operation system that uses foot sole tactile feedback to help operators stabilize bipedal humanoid robots.

Development of a Compact Robust Passive Transformable Omni-Ball for Enhanced Step-Climbing and Vibration Reduction

Kazuo Hongo, Yasunori Kawanami

Robotic Intelligence

🎯 What it does: Developed a compact, robust passive variable omni-wheel (PTOB) to enhance step climbing performance, reduce vibration, and improve structural integrity.

Development of a Low Pressure Pouch Sensor for Force Measurement in Colonoscopy Procedures

Korn Borvorntanajanya, F. R. Y. Baena

🎯 What it does: A low-pressure balloon sensor was developed to be mounted on a colonoscope for measuring contact force with the environment.

Development of a Mobile Reconfigurable Mecanum Robot with a Locking Device of Rollers

Dmitrii N. Zakharov, Botao Zhang

Robotic Intelligence

🎯 What it does: Developed a mobile reconfigurable Mecanum robot capable of switching between omnidirectional and traditional wheel modes, and proposed a pneumatic locking device;

Development of a Modular Robotic Finger for Gripping Various Shaped Objects

Jisu Kim, Dongwon Yun

Robotic Intelligence

🎯 What it does: A modular robotic finger based on p-CFH was developed, employing a single motor lower drive, exhibiting flexibility and shape adaptability, enabling easy grasping of objects with multiple shapes.

Development of a Novel Redundant Parallel Mechanism with Enlarged Workspace and Enhanced Dexterity for Fracture Reduction Surgery

Quan Yuan, Weibang Bai

Robotic IntelligenceBiomedical Data

🎯 What it does: Propose a redundant parallel mechanism (NRPM) based on the Stewart parallel mechanism by adding six redundant degrees of freedom to achieve a larger workspace and higher dexterity, and analyze its kinematics, workspace, and dexterity.

Development of a peristaltic flexible transfer system for transporting feces under microgravity: Construction and validation of transport models

M. Kawano, T. Nakamura

Physics Related

🎯 What it does: Developed a peristaltic flexible transmission system for waste transfer under microgravity, and conducted model construction and experimental validation

Development of a Spherical Wheel-legged Composite Mobile Robot with Multimodal Motion Capabilities

Yuyang Du, Wenfu Xu

Robotic Intelligence

🎯 What it does: Proposed and implemented a spherical wheel-legged hybrid mobile robot capable of switching between foot mode and spherical rolling mode, and designed corresponding control algorithms;

Development of a Super-thin and Fast Omnidirectional Treadmill through a Novel Helical Transmission Mechanism

Sanghun Pyo, Jungwon Yoon

🎯 What it does: Developed a ultra-thin, fast, omnidirectional treadmill utilizing a novel screw drive mechanism

Development of a Throwbot with Shock Absorption Structure

Jaeyeong Keum, Dongwon Yun

Robotic IntelligencePhysics Related

🎯 What it does: Designed and manufactured a throwing robot equipped with an impact absorption structure (paired cross-bending hinge p-CFH and airbag), and verified its performance through free-fall experiments and obstacle crossing tests.

Development of Bidirectional Series Elastic Actuator with Torsion Coil Spring and Implementation to the Legged Robot

Yuta Koda, Kensaku Ishizuka

Robotic Intelligence

🎯 What it does: Develop a compact and lightweight coil spring series elastic actuator (SEA), and implement it in three joints (hip, knee, ankle) of a single-legged robot, verifying its ability to achieve flexible landing and continuous jumping;

Development of Contextual Collision Risk Framework for Operational Envelope of Autonomous Navigation System

In-Chul Kim, Jinmo Park

Autonomous Driving

🎯 What it does: Proposed the Contextual Collision Risk (CCR) method to assess collision risks for autonomous navigation systems in congested maritime areas, and established an operational envelope (OE).

Development of five-finger hand-type robotic forceps for laparoscopic gastrointestinal surgery

Hiroyuki Wakamatsu, Masaya Mukai

Robotic Intelligence

🎯 What it does: Developed a five-fingered robotic forceps suitable for laparoscopic gastrointestinal surgery

Development of Permanent Magnet Elastomer-based Tactile Sensor with Adjustable Compliance and Sensitivity

Devesh Abhyankar, Mitsuhiro Kamezaki

Robotic Intelligence

🎯 What it does: Developed a tactile sensor with adjustable compliance and sensitivity based on permanent magnet elastomer.

DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision

Yutong Hu, Fisher Yu

Robotic Intelligence

🎯 What it does: Designed and implemented a multi-task learning framework enabling legged robots to achieve agile motion strategies when manipulating a soccer ball;

DexSkills: Skill Segmentation Using Haptic Data for Learning Autonomous Long-Horizon Robotic Manipulation Tasks

Xiaofeng Mao, Lorenzo Jamone

SegmentationRobotic IntelligenceSupervised Fine-TuningMultimodality

🎯 What it does: Developed DexSkills, a supervised learning framework that leverages proprioceptive and haptic data to decompose long-duration fine robot manipulation tasks into reusable primitive skills, enabling one-click autonomous execution by robots.

DHP-Mapping: A Dense Panoptic Mapping System with Hierarchical World Representation and Label Optimization Techniques

Tianshuai Hu, Ming Liu

Simultaneous Localization and MappingWorld ModelPoint Cloud

🎯 What it does: Proposes DHP-Mapping, a dense panoptic mapping system that employs hierarchical modeling using multiple TSDF submaps and panoptic labels, capable of simultaneously maintaining geometric and semantic information at both voxel-level and submap-level.

DIABLO: A 6-DoF Wheeled Bipedal Robot Composed Entirely of Direct-Drive Joints

Dingchuan Liu, Ximin Lyu

Robotic Intelligence

🎯 What it does: Designed and implemented a fully direct-driven six-degree-of-freedom wheeled bipedal robot DIABLO, and developed an LQR-based balance controller and a multi-modal motion controller.

DiaGBT: An Explainable and Evolvable Robot Control Framework using Dialogue Generative Behavior Trees

Jinde Liang, Xiaodong Yi

Explainability and InterpretabilityRobotic IntelligenceLarge Language ModelText

🎯 What it does: Proposed a Dialogue Generative Behavior Trees (DiaGBT) framework that converts human natural language instructions into behavior trees for execution by robots, while supporting multi-round human-robot interaction and real-time learning of reusable skills.

Diff-Control: A Stateful Diffusion-based Policy for Imitation Learning

Xiao Liu, H. B. Amor

Diffusion model

🎯 What it does: Proposed a Diff-Control strategy based on diffusion models for imitation learning;

Differentiable Collision-Free Parametric Corridors

Jon Arrizabalaga, Markus Ryll

Autonomous DrivingOptimizationImagePoint Cloud

🎯 What it does: Compute differentiable collision-free parameterized channels that are continuous, smooth, and differentiable.

Differentiable Fluid Physics Parameter Identification By Stirring and For Stirring

Wenqiang Xu, Cewu Lu

Robotic IntelligencePhysics Related

🎯 What it does: Developed a differentiable fitting framework called DiffStir, used for identifying key physical parameters of fluids through stirring and generating robot stirring instructions

Differential-Algebraic Equation Control Barrier Function for Flexible Link Manipulator

Younghwa Park, Christoffer Sloth

OptimizationRobotic IntelligencePhysics RelatedOrdinary Differential Equation

🎯 What it does: Develop and apply control barrier functions based on differential-algebraic equations to ensure the safe operation of a two-link flexible manipulator under position constraints.

DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions

Sanket Kalwar, K. M. Krishna

SegmentationPrompt EngineeringDiffusion modelImage

🎯 What it does: Proposed DiffPrompter, a differentiable visual and latent prompting mechanism, to enhance the semantic segmentation performance of base models under adverse weather conditions.

Diffusion-PbD: Generalizable Robot Programming by Demonstration with Diffusion Features

Michael Murray, Maya Cakmak

Representation LearningRobotic IntelligenceDiffusion modelImage

🎯 What it does: Synthesizing generalizable robot manipulation skills using a single demonstration through representations of pre-trained vision foundation models

DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimation

Takuya Ikeda, Koichi Nishiwaki

Pose EstimationDiffusion modelMultimodality

🎯 What it does: Use diffusion probability models to address symmetry and uncertainty issues in category-level pose estimation.

DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability

Xiaolin Fang, D. Fox

Robotic IntelligenceDiffusion model

🎯 What it does: Propose combining diffusion models with Task and Motion Planning (TAMP) systems, performing multi-step constraint reasoning in partially observable environments using learned samplers and constraint models, and predicting the states of unknown objects by defining samplers and operators on learned latent embedding spaces.

DiPPeST: Diffusion-based Path Planner for Synthesizing Trajectories Applied on Quadruped Robots

Maria Stamatopoulou, Dimitrios Kanoulas

GenerationRobotic IntelligenceDiffusion model

🎯 What it does: Proposed a diffusion model-based image and goal-conditioned quadruped robot trajectory generator called DiPPeST;

Direct TPS-based 3D non-rigid motion estimation on 3D colored point cloud in eye-in-hand configuration

Lénaïc Cuau, Nabil Zemiti

Pose EstimationRobotic IntelligencePoint Cloud

🎯 What it does: Estimate the 3D non-rigid motion of surfaces directly on point clouds using an RGB-D camera in an eye-in-hand configuration.

Discover2Walk: A cable-driven robotic platform to promote gait in pediatric population

Pablo Romero-Sorozábal, Eduardo Rocon

Robotic IntelligenceBiomedical Data

🎯 What it does: Designed and initially evaluated the multi-module, rope-driven rehabilitation robot platform Discover2Walk (D2W) tailored for children, conducting 10 gait rehabilitation sessions with two 6-year-old ambulatory cerebral palsy children and one 4-year-old non-ambulatory child.

Discretizing SO(2)-Equivariant Features for Robotic Kitting

Jiadong Zhou, I-Ming Chen

Pose EstimationRobotic IntelligenceConvolutional Neural NetworkImage

🎯 What it does: Proposed a novel robotic accessory assembly framework that utilizes SO(2) equivariant networks and grouped discrete operations to achieve fine-grained orientation estimation, and developed the Hand-Tool Kitting Dataset for evaluation.

Disentangled Acoustic Fields For Multimodal Physical Scene Understanding

Jie Yin, Chuang Gan

Object DetectionMultimodalityPhysics RelatedAudio

🎯 What it does: Studies multimodal physical scene understanding, proposing a model called Learning Decoupled Acoustic Field (DAF) that uses an analysis-synthesis framework to infer sound source attributes and construct spatial uncertainty maps for locating falling objects.

Distilling Knowledge for Short-to-Long Term Trajectory Prediction

Sourav Das, Lamberto Ballan

Knowledge DistillationVideo

🎯 What it does: Propose the Di-Long method, which uses knowledge distillation from a short-term trajectory prediction model to guide the student network for long-term trajectory prediction.

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression

Fernando Acero, Zhibin Li

Explainability and InterpretabilityKnowledge DistillationRobotic IntelligenceReinforcement Learning

🎯 What it does: Distill neural network policies from reinforcement learning into more interpretable models (GBM, EBM, and symbolic regression), and achieve efficient behavioral cloning through a curriculum-based DAgger algorithm.

Distributed Model Predictive Covariance Steering

A. Saravanos, Evangelos A. Theodorou

Optimization

🎯 What it does: Proposes a distributed model predictive covariance scheduling (DiMPCS) framework for multi-agent control under random uncertainty.

Disturbance-Aware Model Predictive Control of Underactuated Robotics Systems

Jiwon Kim, Min Jun Kim

OptimizationRobotic Intelligence

🎯 What it does: Proposed a disturbance-aware MPC method that estimates disturbances online using a nonlinear disturbance observer and explicitly incorporates the estimate into the model predictive control

DITTO: Demonstration Imitation by Trajectory Transformation

Nick Heppert, A. Valada

Pose EstimationRobotic IntelligenceVideo

🎯 What it does: This paper proposes a two-stage process to achieve one-shot imitation from a single RGB-D video demonstration. The first stage involves offline extraction of demonstration trajectories and segmentation of the manipulated object and its relative motion, while the second stage re-detects objects online, deforms trajectories, and executes them on a robot.

DMFuser: Distilled Multi-Task Learning for End-to-end Transformer-Based Sensor Fusion in Autonomous Driving

Pedram Agand, Mo Chen

Data SynthesisAutonomous DrivingKnowledge DistillationConvolutional Neural NetworkTransformerImage

🎯 What it does: Built DMFuser, a Transformer-based end-to-end perception-control framework that fuses RGB-D camera data and generates vehicle throttle, steering, and braking commands using multi-task knowledge distillation.

DNS-SLAM: Dense Neural Semantic-Informed SLAM

Kunyi Li, Federico Tombari

Simultaneous Localization and MappingImage

🎯 What it does: Proposes DNS-SLAM, a neural RGB-D semantic SLAM method that utilizes 2D semantic priors and hybrid representations, capable of training category-based scene representations and achieving stable camera tracking; simultaneously combines multi-view geometry constraints with image-based feature extraction to output color, occupancy, and semantic category information; to enable high-speed tracking, introduces a lightweight rough scene representation trained with self-supervised learning.

Do One Thing and Do It Well: Delegate Responsibilities in Classical Planning

Tin Lai, Philippe Morere

Optimization

🎯 What it does: Proposed an implicit hierarchical solver framework and algorithm based on the principle of delegation for solving classical planning problems.

DOB-based Wind Estimation of A UAV Using Its Onboard Sensor

Haowen Yu, Ximin Lyu

Autonomous Driving

🎯 What it does: Proposed and implemented a comprehensive wind speed estimation algorithm capable of estimating 3D wind vectors during unmanned aerial vehicle dynamic flight

Domain Adaptation in Visual Reinforcement Learning via Self-Expert Imitation with Purifying Latent Feature

Lin Chen, Danwei Wang

Domain AdaptationReinforcement LearningAuto Encoder

🎯 What it does: Proposes a framework combining self-expert imitation and latent feature purification for domain adaptation in visual reinforcement learning;

Domain Randomization-free Sim-to-Real : An Attention-Augmented Memory Approach for Robotic Tasks

Jia Qu, Shotaro Miwa

Robotic IntelligenceReinforcement Learning

🎯 What it does: Propose the Soft Attention-Augmented Actor-Critic (Soft3AC) architecture to address sim-to-real transfer tasks without requiring domain randomization.

DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment

Yanjiang Guo, Jianyu Chen

Robotic IntelligenceLarge Language ModelVision Language Model

🎯 What it does: Propose the DoReMi framework to achieve real-time detection and recovery of planning and execution errors in robotic tasks using language models.

DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving

Sheng Wang, Junwei Liang

Data SynthesisAutonomous DrivingMixture of ExpertsDiffusion model

🎯 What it does: Proposed an interactive and controllable traffic scene generation framework called DragTraffic, based on conditional diffusion models, enabling non-experts to generate diverse realistic driving scenarios.

DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories

Matteo El-Hariry, Miguel A. Olivares-Méndez

Reinforcement Learning

🎯 What it does: Introduces a system based on deep reinforcement learning for controlling floating platforms in simulation and real environments;

Driving Animatronic Robot Facial Expression From Speech

Boren Li, Hangxin Liu

GenerationRobotic IntelligenceAudio

🎯 What it does: Propose a voice-driven method for generating realistic animated robot facial expressions based on linear blend skinning (LBS), capable of producing expressions in real-time at high frame rates.

Driving from Vision through Differentiable Optimal Control

Flavia Sofia Acerbo, Tong Duy Son

Autonomous DrivingOptimizationExplainability and InterpretabilityImage

🎯 What it does: Proposes the DriViDOC framework to achieve end-to-end learning from visual inputs to differentiable optimal control, generating an autonomous driving controller.

Driving Style Alignment for LLM-powered Driver Agent

Ruoxuan Yang, Jiangtao Gong

Autonomous DrivingReinforcement Learning from Human FeedbackTransformerLarge Language ModelAgentic AIText

🎯 What it does: Proposed a multi-alignment framework that aligns LLM-driven driving agents with human driving styles through demonstration and feedback, constructed a natural language human driving behavior dataset based on natural driving experiments and subsequent interviews, validated its effectiveness in the CARLA simulation environment, and further supported it with human evaluations;

DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences

Yidong Huang, Joyce Chai

Autonomous DrivingRobotic IntelligenceTransformerLarge Language ModelVision Language ModelVideoText

🎯 What it does: Developed a video-language model agent named DriVLMe, integrating embodied experiences from simulated environments with social experiences from real human dialogues to enable natural and effective communication between humans and autonomous vehicles.

Drones Guiding Drones: Cooperative Navigation of a Less-Equipped Micro Aerial Vehicle in Cluttered Environments

Václav Pritzl, M. Saska

Robotic IntelligenceSimultaneous Localization and MappingPoint Cloud

🎯 What it does: This paper enables the secondary micro UAV to autonomously navigate in unknown, GPS-restricted crowded environments with limited sensing capabilities by assigning the sensing task to the host UAV.

DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation

Huixin Zhang, Hesheng Wang

Pose EstimationAutonomous DrivingSimultaneous Localization and MappingPoint Cloud

🎯 What it does: Propose a 3D point cloud sequence learning model DSLO based on inconsistent spatiotemporal propagation for LiDAR odometry.

DSVT: Dynamic 3D Surround View for Tractor-Trailer Vehicles Based on Real-Time Pose Estimation with Drop Model

Zhipeng Dong, Yi Yang

Pose EstimationAutonomous Driving

🎯 What it does: Proposed a dynamic 3D panoramic view system (DSVT) for tractors-trailers.

DTG : Diffusion-based Trajectory Generation for Mapless Global Navigation

Jing Liang, Dinesh Manocha

Autonomous DrivingRecurrent Neural NetworkDiffusion model

🎯 What it does: Developed an end-to-end trajectory generation method DTG based on diffusion models for mapless global navigation

Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video

Tao Tang (Peking University), Wenhao Li (Peking University)

Pose EstimationGraph Neural NetworkTransformerVideoMesh

🎯 What it does: Propose a dual-branch graph Transformer network (DGTR) for reconstructing 3D human meshes from monocular videos

Dual-Process Optimization for Multi-Vehicle Route Planning and Parts Collection Sequencing

Ryota Higa, Florence Ho

Optimization

🎯 What it does: Proposed a dual-process optimization method for multi-vehicle route planning and determining the sequence of part collection in a parts warehouse.

DuCAS: a knowledge-enhanced dual-hand compositional action segmentation method for human-robot collaborative assembly

Hao Zheng, Xun Xu

SegmentationRobotic IntelligenceLarge Language Model

🎯 What it does: Proposes a knowledge-enhanced method for segmenting dual-hand composite actions (DuCAS)

Dung Beetle Optimizer-based High-precision Localization for Magnetic-Controlled Capsule Robot *

Zijin Zeng, Lin Feng

OptimizationRobotic IntelligencePhysics Related

🎯 What it does: Proposed a high-precision localization method for magnetic capsule robots based on the Dung Beetle Optimizer.

DVT: Decoupled Dual-Branch View Transformation for Monocular Bird’s Eye View Semantic Segmentation

Jiayuan Du, Qi Chen

SegmentationAutonomous DrivingImage

🎯 What it does: Propose a dual-branch view transformation (DVT) framework to achieve monocular bird's-eye view semantic segmentation.

Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraints

Eric Hannus, Ville Kyrki

Robotic IntelligenceReinforcement Learning

🎯 What it does: Proposes a dynamic deformable object manipulation framework leveraging imitation learning and adapting to hardware constraints, applied to the bag-opening task.

Dynamic Model and Experimental Validation of a Haptic Robot based on a Flexible Antenna mounted on an Omnidirectional Platform

Luis Mérida-Calvo, V. F. Batlle

Robotic IntelligencePhysics Related

🎯 What it does: Developed a dynamic model for an omni-directional robot with a flexible sensing antenna and conducted experimental validation.

Dynamic Modeling of Robotic Fish considering Background Flow using Koopman Operators

Xiaozhu Lin, Yang Wang

Robotic Intelligence

🎯 What it does: Proposed a flow-aware robotic fish dynamic model called FARM, which incorporates background flow and uses the Koopman operator to achieve linear approximation for predicting the next state.

Dynamic Object Catching with Quadruped Robot Front Legs

Andr'e Schakkal, A. Ijspeert

Object DetectionObject TrackingRobotic IntelligenceConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: This paper proposes a framework that utilizes the front paws of a quadruped robot to perform dynamic grasping while the rear legs are supporting, combining computer vision, trajectory prediction, and leg control to enable the robot to detect, track, and capture thrown objects via an onboard camera;

Dynamic Reconfiguration Integrated Nested A*: A Path Planner for Reconfigurable Robot to Improve Performance in Confined Spaces

W. K. R. Sachinthana, M. R. Elara

OptimizationRobotic Intelligence

🎯 What it does: Proposed a dynamic reconfiguration-based path planning method (DRiNA*) for navigation of reconfigurable robots in confined spaces.

Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement

Zhiqiang Hu, Masatoshi Ishikawa

RestorationTransformerImage

🎯 What it does: Proposed and implemented Dynamic SpectraFormer, which enhances underwater images using a frequency-domain transformer, capable of simultaneously correcting high- and low-frequency mixed distortions.

Dynamic Throwing with Robotic Material Handling Machines

Lennart Werner, Marco Hutter

Robotic IntelligenceReinforcement Learning

🎯 What it does: Designed and implemented a dynamic throwing controller for heavy logistics robotic arms using reinforcement learning, enabling the robotic arms to perform dynamic throwing actions through passive joints, significantly improving work efficiency and the throwing workspace;

Dynamic Walking on Highly Underactuated Point Foot Humanoids: Closing the Loop between HZD and HLIP

Adrian B. Ghansah, A. Ames

Robotic Intelligence

🎯 What it does: Developed and implemented a dynamic gait walking control framework for the point-foot humanoid robot ADAM.

Dynamic-Range Focal Sweep: Seamless Continuous Autofocus Based on High-Speed Vision for Magnified Object Tracking

Tianyi Zhang, Akio Namiki

Object TrackingVideo

🎯 What it does: Proposes a continuous autofocus (C-AF) method based on high-speed vision, utilizing dynamic range focal sweep to achieve continuous focusing and tracking of small, fast-moving objects at high magnification.

Dynamically Modulating Visual Place Recognition Sequence Length For Minimum Acceptable Performance Scenarios

Connor Malone, Michael Milford

RecognitionImage

🎯 What it does: Proposes a method for dynamically adjusting the sequence length in visual place recognition by fitting a model on a calibrated dataset, which can minimize the required sequence length while meeting the target localization performance.

Dynamics-Based Trajectory Planning for Vibration Suppression of a Flexible Long-Reach Robotic Manipulator System

A. Chen, Kaiqiang Zhang

OptimizationRobotic IntelligenceTime Series

🎯 What it does: Proposed a dynamics-based trajectory optimization method for suppressing vibrations in flexible long-arm manipulators;

EasyHeC++: Fully Automatic Hand-Eye Calibration with Pretrained Image Models

Zhengdong Hong, Linghao Chen

OptimizationRobotic IntelligenceConvolutional Neural Network

🎯 What it does: Developed a fully automatic hand-eye calibration framework called EasyHeC++, capable of accurately calibrating any robotic arm under markerless and training-free conditions.

EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union

Brian Hsuan-Cheng Liao, Alois Knoll

Object DetectionAutonomous DrivingImagePoint Cloud

🎯 What it does: Proposed the Ego-Centric Intersection-over-Union (EC-IoU) method, which improves the traditional IoU through a weighted mechanism, making it focus more on the predicted regions close to the target from the subject's perspective, thereby enhancing safety-related performance in navigation scenarios.

Effect of Tactile and Deep Sensory Feedback Synchronized with the Manipulation of Myoelectric Hand on Body Recognition

Rintaro Hamaoka, Ryu Kato

Recognition

🎯 What it does: Developed a wearable, operable electromyographic prosthetic hand that synchronizes hand control through tactile and deep sensory feedback, exploring its impact on body cognition

Effects of fiber number and density on fiber jamming: Towards follow-the-leader deployment of a continuum robot

Chen Qian, Liao Wu

Robotic Intelligence

🎯 What it does: Design and manufacture a fiber jamming module (FJM) with a diameter of 4 mm, and study the effects of fiber number and filling density on absolute stiffness and stiffness variation through theoretical and experimental analysis, while verifying its feasibility in medical follower-leading (FTL) robots.

Efficient Balance Detection for Modular Robots

Ikrame Yazidi, J. Bourgeois

Computational EfficiencyRobotic Intelligence

🎯 What it does: Developed a distributed algorithm to achieve balance detection for modular robots under real-time conditions.

Efficient Dynamic LiDAR Odometry for Mobile Robots with Structured Point Clouds

Jonathan Lichtenfeld, O. Stryk

Robotic IntelligenceSimultaneous Localization and MappingPoint Cloud

🎯 What it does: Proposes a real-time dynamic LiDAR odometry pipeline for mobile robots in urban search and rescue.

Efficient Estimation of Frequency Response Functions of Industrial Robots Using the Local Rational Method

Stefanie A. Zimmermann, S. Moberg

Computational EfficiencyRobotic Intelligence

🎯 What it does: This paper applies the locally parameterized FRF estimation method to the frequency response function estimation of a 6-axis robotic arm to reduce experimental time and data volume, and conducts experimental analysis of the results.

Efficient Extrinsic Self-Calibration of Multiple IMUs using Measurement Subset Selection

Jongwon Lee, T. Bretl

Computational Efficiency

🎯 What it does: Proposed and verified an efficient method using measurement subset selection in multi-IMU extrinsic parameter self-calibration.

Efficient Feature Mapping Using a Collaborative Team of AUVs

Benjamin Biggs, James McMahon

Robotic IntelligenceSimultaneous Localization and Mapping

🎯 What it does: Conduct experiments using a group of small autonomous underwater vehicles to determine the position of contour lines

Efficient Global Trajectory Planning for Multi-robot System with Affinely Deformable Formation

Hao Sha, Yue Wang

OptimizationRobotic IntelligenceReinforcement Learning

🎯 What it does: Proposed a front-end and back-end framework for global trajectory planning in multi-robot systems under affine deformable formations.