← Search

Zhidong Wang

10 accepted papers

2026

AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving

ICML 2026poster

Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either struggle to resolve distribution misalignment between reasoning an…

Cited by 0SourcecodeScholar
2024

Bio-Inspired Pupal-Mode Actuator with Ultra-Crossing Capability for Soft Robots

ICRA 2024poster

Robot-assisted Natural Orifice Translu-minal Endoscopic Surgery (NOTES) represents a paradigm shift in surgical practice, significantly mini-mizing patient morbidity. However, the variability of inner diameter and the inter-luminal crossing within the luminal tracts lead to challenge for effective r…

Cited by 0SourceScholar
2022

Shape Sensing for Continuum Robots by Capturing Passive Tendon Displacements With Image Sensors

RA-L 2022

Continuum robots and soft robots have shown great potential in industrial and medical applications. Sensing the shapes of continuum robots is a challenging but significant problem for enhancing their performance during various tasks. In this letter, we present a novel method to estimate the shapes o

Cited by 18SourceScholar
2021

A Magnetic Continuum Robot With Multi-Mode Control Using Opposite-Magnetized Magnets

RA-L 2021

Magnetic field-controlled continuum robots can be steered dexterously within a small dimension. However, their dexterity, generally being restricted to C-shape, is not sufficient for most practical applications, e.g., avoiding obstacles to reach the target region, fixing the tip orientation, or pass

Cited by 62SourceScholar
2021

GR-Fusion: Multi-sensor Fusion SLAM for Ground Robots with High Robustness and Low Drift

IROS 2021poster

This paper presents a tightly coupled pipeline, which efficiently fuses measurements of LiDAR, camera, IMU, encoder, and GNSS to estimate the robot state and build a map even in challenging situations. The depth of visual features is extracted by projecting the LiDAR point cloud and ground plane int…

Cited by 21SourceScholar
2020

Design and Modeling of a Parallel Shifted-Routing Cable-Driven Continuum Manipulator for Endometrial Regeneration Surgery

IROS 2020poster

Endometrial regeneration surgery is a new therapy for intrauterine adhesion (IUA). However, existing instruments lacking dexterity and compliance are with difficulty to successfully perform the tasks of generating transplant wounds and transplanting stem cells during endometrial regeneration surgery…

Cited by 9SourceScholar
2020

GR-SLAM: Vision-Based Sensor Fusion SLAM for Ground Robots on Complex Terrain

IROS 2020poster

In recent years, many excellent SLAM methods based on cameras, especially the camera-IMU fusion (VIO), have emerged, which has greatly improved the accuracy and robustness of SLAM. However, we find through experiments that most of the existing VIO methods perform well on drones or drone datasets, bu…

Cited by 11SourceScholar
2017

A Contact-Aided Asymmetric Steerable Catheter for Atrial Fibrillation Ablation

RA-L 2017

Electrical isolation using the ablation catheter has been widely used as the golden standard for the treatment of atrial fibrillation. Clinical practice shows that the tip orientation affects the formation of the effective lesion size. However, the traditional unidirectional or bidirectional cathete

Cited by 19SourceScholar
2015

A cross-helical tendons actuated dexterous continuum manipulator

IROS 2015poster

S shape dexterous continuum manipulators (DCMs) are preferred in minimally invasive surgeries for better steerability towards a target and obstacles avoidance capability. Current ways of realizing S shapes need to combine multi-bending segments which need to control the different segment separately.…

Cited by 27SourceScholar