Human-Inspired Robotic Grasp Control With Tactile Sensing

By Joseph M. Romano, Kaijen Hsiao, G. Niemeyer, Sachin Chitta, K. Kuchenbecker. IEEE Transactions on robotics, 2011

444 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/71987e3262109112b93f1db18df74713271c7bdf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Control and Systems Engineering

Citations in the corpus

Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks (2018, background): “robotics [7, 45, 48, 54], the proposed manipulation strategies are often task-specific.”
Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks (2019, background): “ng contact-rich manipulation [8], which is illustrated in Fig. 1. Yet few algorithms endow robots with a similar capability. While the utility of multimodal data has frequently been shown in robotics [7, 20, 54, 58, 66], the proposed manipulation strategies often rely on handcrafted features or prio”
Implementation of a robot-human object handover controller on a compliant underactuated hand using joint position error measurements for grip force and load force estimations (2014, background): “The ability to properly control grip force is very important in object manipulation and thus in handovers [19], [20].”
Integrated task and motion planning in belief space (2013, methodology): “To increase robustness in grasping objects, we employ a simple reactive grasping procedure (Romano et al., 2011) that uses information from touch sensors on the fingers to recover from small errors in an object’s location estimate.”
Learning robot in-hand manipulation with tactile features (2015, background): “can also aid by detecting grasp instabilities and slippage that can occur while manipulating an object [13, 20, 24, 25].”
Data-Driven Grasp Synthesis—A Survey (2013, background): “This provides a natural precursor to reactive grasping [23, 24, 25, 26, 27], which, given a grasp hypothesis, considers the problem of robustly acquiring it under uncertainty.”
Towards learning hierarchical skills for multi-phase manipulation tasks (2015, methodology): “Previous work in robotics has already shown the benefits of incorporating phases into the design of controllers [32], [10], and several methods have been proposed for learning controllers for multi-phase tasks [22], [26], [1], [28].”
The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes? (2017, unknown): “In manipulation, the use of tactile sensors has been demonstrated for detecting and compensating for slip [3, 4, 5], and for grasping fragile objects [6].”
Learning of grasp adaptation through experience and tactile sensing (2014, background): “To alleviate the uncertainty of these physical properties of the object, an additional grasping force controller is usually employed to carefully adapt the grasping forces to unknown object weight and friction conditions at the contact points [14].”
A Review of Tactile Information: Perception and Action Through Touch (2020, unknown): “tact is to compare the measured tactile signals with a given threshold [65], [88], which is estimated from previous contact”
More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch (2018, background): “Works such as [20], [21], [22] extracted features from tactile signals to detect/predict slip, so as to adaptively adjust the grasping force.”
Tactile sensing in dexterous robot hands - Review (2015, background): “Detection of a slip and texture recognition.”