#RobotSensingSystems
LightNews LightNews
ieeetro.bsky.social
In a recent T-RO paper, researchers show how complex manipulation tasks that require both precise reaching and controlled slipping or sliding can benefit from see-through visuotactile sensing.
ieeexplore.ieee.org/document/108...

#RobotSensingSystems #TactileSensor #ImitationLearning
Our STS sensor before and during contact (right column) with a cabinet knob (middle column) during a door opening task (left column). In visual mode, the camera sees through the gel membrane, allowing the knob to be found, while tactile mode provides contact-based feedback, via gel deformation and resultant dot displacement, upon initial contact and during opening. Red circles highlight the knob in the sensor view.
April 2, 2025 at 3:12 PM
ieeetro.bsky.social
Presenting a dynamic model‑based cooperative tracking control for both position and orientation of a tensegrity continuum robot’s end‑effector—achieving precise, cooperative movement via a dynamic model.
ieeexplore.ieee.org/abstract/doc...

#ContinuumRobots #RobotSensingSystems
Fabrication of the TCR. (a) Compliant tensegrity joint. (b) Assembly by the tensegrity joints. (c) Body structure of the TCR. (d) 3-D printing experimental prototype.
August 28, 2025 at 8:41 PM
ieeetro.bsky.social
A T-RO King-Sun Fu Award Honorable Mention paper develops reactive modulation techniques on manifolds for safe navigation around complex, non-convex obstacles in real-time.
ieeexplore.ieee.org/document/104...

Authors: Christopher K. Fourie, Nadia Figueroa, and Julie Shah

#RobotSensingSystems
Proposed modulation approach applied to the end-effector of a robot manipulator as a real-time, reactive, motion planner. Our method is able to navigate around nonconvex obstacles with a control frequency of 1 kHz, while updating the obstacle states at 100 Hz.
July 7, 2025 at 4:30 PM
ieeetro.bsky.social
Researchers propose a compact 6D suction cup model that reduces parameter count from 21 to just 5 via symmetry reduction, achieving ~5 mm and 3° accuracy and robust force estimation even at 60° gripper tilt.
ieeexplore.ieee.org/document/109...

#RobotSensingSystems #RobotManipulator
Example of a robotic bin-to-bin application where the deformation of an active bellow suction cup is clearly visible. Our proposed model allows to accurately predict this deformation enabling new robotic manipulation tasks. The particular shows the parts of a suction cup: 1) Fitting 2) Bellows 3) Lip.
October 1, 2025 at 7:20 PM
ieeetro.bsky.social
Authors introduce a method that automatically selects sensor models and relevant state variables from runtime data—no prior knowledge needed. It integrates into localization frameworks with built-in false-positive checks
ieeexplore.ieee.org/document/110...

#RobotSensingSystems
Generalized setup of transformations to express various sensor modalities such as vectors for the magnetic field or the velocity and transformations for 3-DoF and 6-DoF sensor measurements and calibrations. This work aims to process a gray-box sensor signal together with a reliable system state to identify a corresponding sensor model and its properties.
November 7, 2025 at 11:01 PM
ieeetro.bsky.social
T-RO Honorable Mention paper entitled “Task and Motion Planning for Execution in the Real” introduces a framework integrating task and motion planning for real-world robotic execution under uncertainty, improving adaptability
ieeexplore.ieee.org/document/105...

#RobotSensingSystems #Robotics
Task is to move three objects to the goal tray. The full states of the dotted objects are not known precisely. A task and motion plan will have gaps, which can only be filled in during execution, e.g., the blue object's pose can only be known after opening the drawer. The problem imposes constraints visualized in a block-world-like diagram at the lower part of the figure.
July 11, 2025 at 11:45 AM
ieeetro.bsky.social
The challenges of mapping dynamic environments. Particle-based instance-aware semantic occupancy map jointly estimates occupancy, semantics, and instance IDs to improve robustness and accuracy.
ieeexplore.ieee.org/document/108...

#RobotSensingSystems
World model illustration. (a) Example scenario with both objects of interests and background objects. The wall and ground belong to the background object with ID 1. The tree belongs to the background object with ID 2. The car and the two robots belong to the objects of interest with ID 3, 4 and 6, respectively, and are dynamic objects. The mailbox with ID 5 is an example static object of interests. Each object is assumed to be composed of a set of points on its surface. The set of the Ith object is marked as XI and the points within the set share the same color. (b) Particles (hollow points) that are used to model the PHD of the points. Particles with different IDs are shown in different colors. Particles with the same ID share the same motion. The particles are stored in voxel subspaces [15], which are also used for resampling and occupancy estimation. (c) Camera pinhole model used in this work to formulate the pyramid subspaces [15], which are used to distinguish the observed area and occluded area in the continuous space and to accelerate the update process. The green point is a measurement point in a pyramid subspace. The gray area behind the measurement point is occluded. Only a part of the points in X1 in (a), voxel subspaces in (b), and pyramid subspaces in (c) are shown for clear illustration.
April 11, 2025 at 9:17 PM