Dr Dandan Zhang
ROBOTICS · AI · EDUCATION
IMPERIAL COLLEGE LONDON
Intelligent Dexterous Manipulation
Contact-rich manipulation across scales.
How can robots maintain useful contact while moving and handling objects?
Six selected outcomes connect tactile grippers, coordinated robots and magnetic micromanipulation. Each study tests a specific capability on a physical platform.
Research overview · All publications
01 / TACTILE GRASPING & COORDINATED MANIPULATION
MagicGripper · Sensing before and during contact
IEEE Transactions on Automation Science and Engineering · 2025 · Journal article
Outcome. Mini-MagicTac fingertips combine vision, proximity and touch in one gripper. Contact localisation, force estimation and robustness tests support assembly, alignment and grasping demonstrations.
TacPalm · Gentle grasping with a sensing palm
IEEE Sensors Journal · 2024 · Journal article
Outcome. A tactile palm supports contact detection, grasp-pose adjustment and loss-of-contact detection without stiffening the soft fingers. The complete strategy achieved 97% grasp success and sub-millimetre placement precision in the reported tests.
Bi-Touch · Two arms learning through touch
IEEE Robotics and Automation Letters · 2023 · Journal article
Outcome. Tactile reinforcement-learning policies transfer from simulation to a dual-arm robot for pushing, reorienting and gathering. Physical tests examine unseen objects and disturbances, including the effect of the simulation-to-reality gap on contact forces.
Open paper · Project, code and videos
TacMMs · Cooperative mobile manipulation
IEEE Robotics and Automation Letters · 2023 · Journal article
Outcome. Mobile robots use tactile feedback to adjust their contact with a shared load. In the two-robot lifting study, average success was 66% with tactile feedback versus 34% for the tested visual-only approach.
02 / MAGNETIC MICROMANIPULATION
Mag-VLA · Language-guided microrobot actions
MARSS · 2026 · Conference paper
Outcome. Microscope images and language instructions guide two magnetic actuators controlling an untethered microrobot. Tests demonstrate object approach and transport inside a vascular phantom: approach reached 90% success, while transport remained more challenging across the three task configurations.
Bi-CAST · Adaptive shared magnetic control
IROS · 2026 · Accepted conference paper
Outcome. A context-aware controller adjusts human–robot authority while haptic feedback communicates risk. An eight-participant study across three phantom-navigation tasks found fewer collisions and lower workload than the tested fixed-authority and switching baselines.
Related research: adaptive policies and multi-agent coordination · dexterous teleoperation. Original Mag-VLA research figure and the detailed TacFR-Gripper presentation follow.
 Add a TitleDescribe your image |  Add a TitleDescribe your image |  Add a TitleDescribe your image |
|---|---|---|
 Add a TitleDescribe your image |  Add a TitleDescribe your image |  Add a TitleDescribe your image |
TacFR-Gripper: A Reconfigurable Fin Ray-Based Compliant Robotic Gripper
with Tactile Skin for In-Hand Manipulation
This paper introduces the TacFR-Gripper, a reconfigurable Fin Ray-based soft and compliant robotic gripper equipped with tactile skin, which can be used for dexterous in-hand manipulation tasks. This gripper can adaptively grasp objects of diverse shapes and stiffness levels. An array of Force Sensitive Resistor (FSR) sensors is embedded within the robotic finger to serve as the tactile skin, enabling the robot to perceive contact information during manipulation. We provide theoretical analysis for gripper design, including kinematic analysis, workspace analysis, and finite element analysis to identify the relationship between the gripper's load and its deformation. Moreover, we implemented a Graph Neural Network (GNN)-based tactile perception approach to enable reliable grasping without accidental slip or excessive force.
Three physical experiments were conducted to quantify the performance of the TacFR-Gripper. These experiments aimed to i) assess the grasp success rate across various everyday objects through different configurations, ii) verify the effectiveness of tactile skin with the GNN algorithm in grasping, iii) evaluate the gripper's in-hand manipulation capabilities for object pose control.
The experimental results indicate that the TacFR-Gripper can grasp a wide range of complex-shaped objects with a high success rate and deliver dexterous in-hand manipulation. Additionally, the integration of tactile skin with the GNN algorithm enhances grasp stability by incorporating tactile feedback during manipulations.
