Object Handovers: A Review for Robotics

Ortenzi, Valerio; Cosgun, Akansel; Pardi, Tommaso; Chan, Wesley P.; Croft, Elizabeth A.; Kulić, Dana

doi:10.1109/tro.2021.3075365

Cited by 96 publications

(96 citation statements)

References 197 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Slip can be disastrous (e.g., when transporting a fragile object) or advantageous (e.g., when pushing an object without lifting it) depending on the context [3]. In robotics, the well-studied 'handover' task, which involves passing an object from a robot hand to a human hand, requires control of the gripping force with accuracy and speed to avoid significant slip [4]. The requisite feedback can only be provided through tactile sensing [5] and, consequently, the detection and control of slip is fundamental to the completion of handovers and many other tasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Detect Slip with Barometric Tactile Sensors and a Temporal Convolutional Neural Network

Grover,

Nadeau,

Grebe

et al. 2022

Preprint

View full text Add to dashboard Cite

The ability to perceive object slip via tactile feedback enables humans to accomplish complex manipulation tasks including maintaining a stable grasp. Despite the utility of tactile information for many applications, tactile sensors have yet to be widely deployed in industrial robotics settings; part of the challenge lies in identifying slip and other events from the tactile data stream. In this paper, we present a learningbased method to detect slip using barometric tactile sensors. These sensors have many desirable properties including high durability and reliability, and are built from inexpensive, offthe-shelf components. We train a temporal convolution neural network to detect slip, achieving high detection accuracies while displaying robustness to the speed and direction of the slip motion. Further, we test our detector on two manipulation tasks involving a variety of common objects and demonstrate successful generalization to real-world scenarios not seen during training. We argue that barometric tactile sensing technology, combined with data-driven learning, is suitable for many manipulation tasks such as slip compensation.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Final grasp within 6 cm of the initial grasp position 4. Final grasp between 6-12 cm of the initial grasp position.…”

mentioning

confidence: 99%

Learning to Detect Slip with Barometric Tactile Sensors and a Temporal Convolutional Neural Network

Grover,

Nadeau,

Grebe

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Robots supporting people in their daily activities at home or at the workplace need to accurately and robustly perceive objects, such as containers, and their physical properties, for example when they are manipulated by a person prior to a human-to-robot handover [1,2,3,4,5]. Audio-visual perception should adapt -on-the-fly and with limited or no prior knowledge -to changing conditions in order to guarantee the correct execution of the task and the safety of the person.…”

Section: Introductionmentioning

confidence: 99%

“…Audio-visual perception should adapt -on-the-fly and with limited or no prior knowledge -to changing conditions in order to guarantee the correct execution of the task and the safety of the person. For assistive scenarios at home, audio-visual perception should accurately and robustly estimate the physical properties (e.g., weight and shape) of household containers, such as cups, drinking glasses, mugs, bottles, and food boxes [1,4,6,7,8]. However, the material, texture, transparency and shape can vary considerably across containers and also change with their content, which may not be visible due to the opaqueness of the container or occlusions, and hence should be inferred through the behaviour of the human [1,7,8,9,10].…”

Section: Introductionmentioning

confidence: 99%

Audio-Visual Object Classification for Human-Robot Collaboration

Xompero¹,

Pang²,

Patten³

et al. 2022

Preprint

View full text Add to dashboard Cite

Human-robot collaboration requires the contactless estimation of the physical properties of containers manipulated by a person, for example while pouring content in a cup or moving a food box. Acoustic and visual signals can be used to estimate the physical properties of such objects, which may vary substantially in shape, material and size, and also be occluded by the hands of the person. To facilitate comparisons and stimulate progress in solving this problem, we present the CORSMAL challenge and a dataset to assess the performance of the algorithms through a set of well-defined performance scores. The tasks of the challenge are the estimation of the mass, capacity, and dimensions of the object (container), and the classification of the type and amount of its content. A novel feature of the challenge is our real-to-simulation framework for visualising and assessing the impact of estimation errors in human-to-robot handovers.

show abstract

“…Estimating the physical properties of objects is fundamental for the success and safety of human-robot collaboration [1]. A robot is a completely autonomous system and is supposed to extract information of the target object in order to assist the human correctly.…”

Section: Introductionmentioning

confidence: 99%

Container Localisation and Mass Estimation with an RGB-D Camera

Apicella¹,

Slavic²,

Ragusa³

et al. 2022

Preprint

View full text Add to dashboard Cite

In the research area of human-robot interactions, the automatic estimation of the mass of a container manipulated by a person leveraging only visual information is a challenging task. The main challenges consist of occlusions, different filling materials and lighting conditions. The mass of an object constitutes key information for the robot to correctly regulate the force required to grasp the container. We propose a single RGB-D camera-based method to locate a manipulated container and estimate its empty mass i.e., independently of the presence of the content. The method first automatically selects a number of candidate containers based on the distance with the fixed frontal view, then averages the mass predictions of a lightweight model to provide the final estimation. Results on the CORSMAL Containers Manipulation dataset show that the proposed method estimates empty container mass obtaining a score of 71.08% under different lighting or filling conditions.

show abstract

Object Handovers: A Review for Robotics

Cited by 96 publications

References 197 publications

Learning to Detect Slip with Barometric Tactile Sensors and a Temporal Convolutional Neural Network

Learning to Detect Slip with Barometric Tactile Sensors and a Temporal Convolutional Neural Network

Audio-Visual Object Classification for Human-Robot Collaboration

Container Localisation and Mass Estimation with an RGB-D Camera

Contact Info

Product

Resources

About