Avishai Sintov

Prof. Avishai Sintov

Tel Aviv University, Tel Aviv, Israel

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 July 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ASAvishai Sintov
Avishai Sintov
SMSteven Macenski
Steven Macenski
ABAndy Borum
Andy Borum
TBTimothy Bretl
Timothy Bretl
We present a novel motion planning strategy for the manipulation of elastic rods with two robotic arms. In previous work, it has been shown that the free configuration space of an elastic rod, i.e., the set of equilibrium shapes of the rod, is a smooth manifold of a finite dimension that can be parameterized by one chart. Thus, a sampling-based planning algorithm is straightforward to implement in the product space of the joint angles and the equilibrium configuration space of the elastic rod. Preliminary results show that planning directly in this product space is feasible. However, solving for the elastic rod's shape requires the numerical solution of differential equations, resulting in an excessive and impractical runtime. Hence, we propose to pre-compute a descriptor of the rod, i.e., a roadmap in the free configuration space of the rod that captures its main-connectivity. By doing so, we can plan the motion of any dual-arm robotic system over this roadmap with dramatically fewer solutions of the differential equations. Experiments using the Open Motion Planning Library (OMPL) show significant runtime reduction by an order of magnitude.

16 November 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
OAOsher Azulay
Osher Azulay
NCNimrod Curtis
Nimrod Curtis
RSRotem Sokolovsky
Rotem Sokolovsky
GLGuy Levitski
Guy Levitski
DSDaniel Slomovik
Daniel Slomovik
ASAvishai Sintov
Avishai Sintov
Tactile sensing is a necessary capability for a robotic hand to perform fine manipulations and interact with the environment. Optical sensors are a promising solution for high-resolution contact estimation. Nevertheless, they are usually not easy to fabricate and require individual calibration in order to acquire sufficient accuracy. In this letter, we propose AllSight , an optical tactile sensor with a round 3D structure designed for robotic in-hand manipulation tasks. AllSight is mostly 3D printed including a novel and simplified fabrication processes. This makes it low-cost, modular, durable and in the size of a human thumb while with a large contact surface. We show the ability of AllSight to learn and estimate a full contact state, i.e., contact position, forces and torsion. With that, an experimental benchmark between various configurations of illumination and contact elastomers are provided. Furthermore, the robust design of AllSight provides it with a unique zero-shot capability such that a practitioner can fabricate the open-source design and have a ready-to-use state estimation model. A set of experiments demonstrates the accurate state estimation performance of AllSight.

17 April 2024 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
EBEran Bamani
Eran Bamani
ENEden Nissinman
Eden Nissinman
IMInbar Meir
Inbar Meir
LKLisa Koenigsberg
Lisa Koenigsberg
ASAvishai Sintov
Avishai Sintov

23 January 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ASAvishai Sintov
Avishai Sintov
AMAndrew S. Morgan
Andrew S. Morgan
AKAndrew Kimmel
Andrew Kimmel
ADAaron M. Dollar
Aaron M. Dollar
KBKostas E. Bekris
Kostas E. Bekris
ABAbdeslam Boularias
Abdeslam Boularias
Fully-actuated, multi-fingered robotic hands are often expensive and fragile. Low-cost, under-actuated hands are appealing but present challenges due to the lack of analytical models. This paper aims to learn a stochastic version of such models automatically from data with minimum user effort. The focus is on identifying the dominant, sensible features required to express hand state transitions given quasi-static motions, thereby enabling the learning of a probabilistic transition model from recorded trajectories. Experiments both with Gaussian Processes (GP) and Neural Network models are included for analysis and evaluation. The metric for local GP regression is obtained with a manifold learning approach, known as Diffusion Maps, to uncover the lower-dimensional subspace in which the data lies and provide a geodesic metric. Results show that using Diffusion Maps with a feature space composed of the object position, actuator angles, and actuator loads, sufficiently expresses the hand-object system configuration and can provide accurate enough predictions for a relatively long horizon. To the best of the authors' knowledge, this is the first learned transition model for such underactuated hands that achieves this level of predictability. Notably, the same feature space implicitly embeds the size of the manipulated object and can generalize to new objects of varying sizes. Furthermore, the learned model can identify states that are on the verge of failure and which should be avoided during manipulation. The usefulness of the model is also demonstrated by integrating it with closed-loop control to successfully and safely complete manipulation tasks.

4 August 2016 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
ASAvishai Sintov
Avishai Sintov
OTOr Tslil
Or Tslil
ASAmir Shapiro
Amir Shapiro
In this paper, we present the swing-up regrasping problem in which an object is manipulated using a robotic arm around a point pinched by the arm's gripper. The aim of the regrasping is to manipulate the object from an initial angle to regrasp it on a new desired angle relative to the gripper. The pinching point functions as a semiactive joint at which the gripper is able to apply only frictional torques on the object to resist its motion. We address the problem by proposing a novel approach that incorporates an impulse-momentum method with a clipped linear quadratic regulator (cLQR) based controller for stabilization on the desired angle. In particular, a suboptimal cLQR controller is presented to deal with the dissipative semiactive joint. The interaction of these methods with the unique property of the semiactive joint is investigated and analyzed. Simulations on a six degrees of freedom manipulator regrasping a bottle validate the proposed approach. Moreover, a full experiment was conducted on a robotic arm to test the approach and the control of a semiactive joint. The simulations and experiment have proven the feasibility of the method.

8 February 2021 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
NKNadav D. Kahanowich
Nadav D. Kahanowich
ASAvishai Sintov
Avishai Sintov
Feasible human-robot collaboration requires intuitive and fluent understanding of human motion in shared tasks. The object in hand provides the most valuable information about the intended task of a human. In this letter, we propose a simple and affordable approach where a wearable force-myography device is used to classify objects grasped by a human. The device worn on the forearm incorporates 15 force sensors that can imply about the configuration of the hand and fingers during grasping. Hence, a classifier is trained to easily identify various objects using data recorded while holding them. To augment the classifier, we propose an iterative approach in which additional signals are taken in real-time to increase certainty about the predicted object. We show that the approach provides robust classification where the device can be taken off and placed back while maintaining high accuracy. The approach also improves the performance of trained classifiers that initially produced low accuracy due to insufficient data or non-optimal hyper-parameters. Classification success rate of more than 97% is reached in a short period of time. Furthermore, we analyze the key locations of sensors on the forearm that provide the most accurate and robust classification.