Aaron M. Dollar

ORCID: 0000-0002-2409-4668
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Robot Manipulation and Learning
  • Soft Robotics and Applications
  • Muscle activation and electromyography studies
  • Robotic Mechanisms and Dynamics
  • Prosthetics and Rehabilitation Robotics
  • Modular Robots and Swarm Intelligence
  • Motor Control and Adaptation
  • Teleoperation and Haptic Systems
  • Manufacturing Process and Optimization
  • Robotic Locomotion and Control
  • Robotic Path Planning Algorithms
  • Advanced Materials and Mechanics
  • Advanced Sensor and Energy Harvesting Materials
  • Hand Gesture Recognition Systems
  • Tactile and Sensory Interactions
  • Micro and Nano Robotics
  • Neuroscience and Neural Engineering
  • Additive Manufacturing and 3D Printing Technologies
  • Stroke Rehabilitation and Recovery
  • Dynamics and Control of Mechanical Systems
  • Innovations in Concrete and Construction Materials
  • Reinforcement Learning in Robotics
  • Control and Dynamics of Mobile Robots
  • Mechanics and Biomechanics Studies
  • Time Series Analysis and Forecasting

Yale University
2015-2024

General Motors (United States)
2024

École Polytechnique Fédérale de Lausanne
2023

University of Twente
2023

Osaka University
2023

George Mason University
2023

Institute of Electrical and Electronics Engineers
2021

Gorgias Press (United States)
2021

Stevens Institute of Technology
2021

University of New Haven
2018

In the nearly six decades since researchers began to explore methods of creating them, exoskeletons have progressed from stuff science fiction commercialized products. While there are still many challenges associated with exoskeleton development that yet be perfected, advances in field been enormous. this paper, we review history and discuss state-of-the-art lower limb active orthoses. We provide a design overview hardware, actuation, sensory, control systems for most devices described...

10.1109/tro.2008.915453 article EN IEEE Transactions on Robotics 2008-02-01

In this paper, we analyze and compare existing human grasp taxonomies synthesize them into a single new taxonomy (dubbed "The GRASP Taxonomy" after the project funded by European Commission). We consider only static stable grasps performed one hand. The goal is to extract largest set of different that were referenced in literature arrange systematic way. provides common terminology define hand configurations important many domains such as human-computer interaction tangible user interfaces...

10.1109/thms.2015.2470657 article EN publisher-specific-oa IEEE Transactions on Human-Machine Systems 2015-09-04

In this paper we present the Yale-CMU-Berkeley (YCB) Object and Model set, intended to be used for benchmarking in robotic grasping manipulation research. The objects set are designed cover various aspects of problem; it includes daily life with different shapes, sizes, textures, weight rigidity, as well some widely tests. associated database provides high-resolution RGBD scans, physical properties geometric models easy incorporation into planning software platforms. A comprehensive...

10.1109/icar.2015.7251504 article EN 2015-07-01

This paper introduces the iRobot-Harvard-Yale (iHY) Hand, an underactuated hand driven by five actuators that is capable of performing a wide range grasping and in-hand repositioning tasks. was designed to address need for durable, inexpensive, moderately dexterous suitable use on mobile robots. The primary focus this will be novel simplified design iHY which developed choosing set target tasks around optimized. Particular emphasis placed development fingers are both firm power grasps...

10.1177/0278364913514466 article EN The International Journal of Robotics Research 2014-02-17

In this article, we present the Yale-Carnegie Mellon University (CMU)-Berkeley (YCB) object and model set, intended to be used facilitate benchmarking in robotic manipulation research. The objects set are designed cover a wide range of aspects problem. includes daily life with different shapes, sizes, textures, weights, rigidities as well some widely tests. associated database provides high-resolution red, green, blue, plus depth (RGB-D) scans, physical properties, geometric models for easy...

10.1109/mra.2015.2448951 article EN IEEE Robotics & Automation Magazine 2015-09-01

The inherent uncertainty associated with unstructured environments makes establishing a successful grasp difficult. Traditional approaches to this problem involve hands that are complex, fragile, require elaborate sensor suites, and difficult control. Alternatively, by carefully designing the mechanical structure of hand incorporate features such as compliance adaptability, in grasping tasks can be more easily accommodated. In paper, we demonstrate novel adaptive compliant grasper objects...

10.1177/0278364909360852 article EN The International Journal of Robotics Research 2010-02-02

In this paper, we present an image and model dataset of the real-life objects from Yale-CMU-Berkeley Object Set, which is specifically designed for benchmarking in manipulation research. For each object, presents 600 high-resolution RGB images, RGB-D images five sets textured three-dimensional geometric models. Segmentation masks calibration information are also provided. These data acquired using BigBIRD Scanning Rig Google Scanners. Together with dataset, Python scripts a Robot Operating...

10.1177/0278364917700714 article EN The International Journal of Robotics Research 2017-03-01

This paper reports recent research efforts to advance the functionality of Unmanned Aerial Vehicles (UAVs) beyond passive observation active interaction with and manipulation objects. The archetypical aerial task - grasping objects during flight is difficult due unstable dynamics rotorcraft coupled object-aircraft motion. In this paper, we analyze key challenges encountered when lifting a grasped object transitioning into laden free-flight. We demonstrate that dynamic load disturbances...

10.1109/icra.2011.5980314 article EN 2011-05-01

Commercially available robotic hands are often expensive, customized for specific platforms, and difficult to modify. In this paper, we present the design of an open-source, low-cost, single actuator underactuated hand that can be created through fast commonly-accessible rapid-prototyping techniques simple, off-the-shelf components. This project establishes adaptive, four-finger utilizing simple 3D-printed components, compliant flexure joints, readily obtainable parts. Modular adjustable...

10.1109/icra.2013.6630954 article EN 2013-05-01

In this paper, we present results from a study of prehensile human hand use during the daily work activities four subjects: two housekeepers and machinists.Subjects wore head-mounted camera that recorded their usage in typical place work.For each subject, 7.45 hours video was analyzed, recording type grasp being used its duration.From data, extracted overall frequency, duration distributions for grasp, common transitions between grasps.The show 80 percent just five grasps machinists 10.The...

10.1109/toh.2013.6 article EN IEEE Transactions on Haptics 2013-02-23

Joint compliance can enable successful robot grasping despite uncertainties in target object location. Compliance also enhances manipulator robustness by minimizing contact forces the event of unintended contacts or impacts. In this paper, we describe design, fabrication, and evaluation a novel compliant robotic grasper constructed using polymer-based shape deposition manufacturing. Joints are formed elastomeric flexures, actuator sensor components embedded tough rigid polymers. The result...

10.1109/tmech.2006.871090 article EN IEEE/ASME Transactions on Mechatronics 2006-04-01

This paper is the first of a two-part series analyzing human grasping behavior during wide range unstructured tasks. The results help clarify overall characteristics hand to inform many domains, such as design robotic manipulators, targeting rehabilitation toward important functionality, and designing haptic devices for use by hand. It investigates properties objects grasped two housekeepers machinists course almost 10,000 grasp instances correlates types used object. We establish an object...

10.1109/toh.2014.2326871 article EN IEEE Transactions on Haptics 2014-07-01

This work contributes to the development of a common framework for discussion and analysis dexterous manipulation across human robotic domains.An overview previous is first provided along with an tradeoffs between arm hand dexterity.A hand-centric motion-centric classification then presented applied in four different ways.It discussed how taxonomy can be used identify strategy.Then, applications robot engineering design are explained.Finally, three activities daily living (ADLs) distinguish...

10.1109/toh.2012.53 article EN IEEE Transactions on Haptics 2012-10-18

Characterizing the quasi-stiffness and work of lower extremity joints is critical for evaluating human locomotion designing assistive devices such as prostheses orthoses intended to emulate biological behavior legs. This aims establish statistical models that allow us predict ankle net mechanical adults walking on level ground. During stance phase walking, joint propels body through three distinctive phases nearly constant stiffness known each phase. Using a generic equation moment obtained...

10.1371/journal.pone.0059935 article EN cc-by PLoS ONE 2013-03-21

This paper presents a study on the usage frequency of different grasp types throughout daily functions professional house maid and machinist. Subjects wore head-mounted camera that recorded their hand during work activities. video was then analyzed, recording type associated time stamps, as well information related to task object. The results show nearly 80% used just six grasps machinist nine. data, in conjunction with established taxonomies, will enable better understanding how people...

10.1109/icra.2011.5980366 article EN 2011-05-01

Classical robotic approaches to tactile object identification often involve rigid mechanical grippers, dense sensor arrays, and exploratory procedures (EPs). Though EPs are a natural method for humans acquire information, evidence also exists meaningful property inference from brief, non-exploratory motions (a 'haptic glance'). In this work, we implement feature extraction techniques on data acquired during single, unplanned grasp with simple, underactuated robot hand equipped inexpensive...

10.1109/toh.2016.2521378 article EN IEEE Transactions on Haptics 2016-01-25

This paper presents a high-level discussion of dexterity in robotic systems, focusing particularly on manipulation and hands. While it is generally accepted the robotics community that desirable end effectors with in-hand capabilities should be developed, there has been little, if any, formal description why this needed, given increased design control complexity required. will overview various definitions used literature highlight issues related to specific metrics quantitative analysis. It...

10.1109/icar.2011.6088576 article EN 2021 20th International Conference on Advanced Robotics (ICAR) 2011-06-01

Although grasping and manipulation are key aspects of a robotic system's functionality, researchers often only have limited selection end effectors compatible with their manipulator base. This may either restrict the full range capabilities or force to compensate for effector's intrinsic mechanical disadvantages through compensatory, nonoptimal control strategies. Advances in three-dimensional (3-D) printing enabled quickly customize mechanisms specific tasks, but product is usually not...

10.1109/mra.2016.2639034 article EN IEEE Robotics & Automation Magazine 2017-02-20

This paper presents an analysis of the human biomechanical considerations related to development lower limb exoskeletons. Factors such as kinematic alignment and compatibility, joint range motion, maximum torque, bandwidth are discussed in framework a review design specifications for exoskeleton prototypes literature. From this analysis, we discuss major gaps research topic how those might be filled.

10.1109/icorr.2011.5975366 article EN IEEE International Conference on Rehabilitation Robotics 2011-06-01

In this paper, we present a technique for increasing the strength of thermoplastic fused deposition manufactured printed parts while retaining benefits process such as ease, speed implementation, and complex part geometries. By carefully placing voids in filling them with high-strength resins, can improve overall stiffness by up to 45% 25%, respectively. We discuss parameters necessary use strengthening theoretically possible improvements bending beam members. then show three-point bend...

10.1371/journal.pone.0122915 article EN cc-by PLoS ONE 2015-04-16

In this paper we show that it is possible to design underactuated robot hands capable of performing dexterous manipulation tasks, despite the fact motion an hand not fully constrained by its actuators. If a has elastic elements at joints, then velocity actuators can be mapped onto grasped object using averaging. This mapping used compute classical measures manipulability for hand. We also demonstrate holonomically grasps analyzed determine manifold stable configurations reached from some...

10.1109/icra.2011.5980263 article EN 2011-05-01
Coming Soon ...