Rajiv Dubey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rajiv Dubey has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Redwan Alqasemi
University of South Florida
9 shared publications - Sudeep Sarkar
University of South Florida
3 shared publications - Sujal Vijayaraghavan
Department of Computer Science
2 shared publications - Urvish Trivedi
Department of Mechanical Engineering, University of South Florida, Tampa, FL 33620, USA
2 shared publications - Dimitrios Menychtas
Department of Physical Education and Sport Science, Democritus University of Thrace, 69100 Komotini, Greece
1 shared publication - Faith El Massari
University of South Florida
1 shared publication
Latest Publications
- 14 September 2026
- Published by Springer Nature
- p. 55-64
A Velocity Analysis Framework for 2-DOF Above-Knee Prosthetic Legs via DH Based Jacobian Kinematics
- 14 September 2026
- Published by Springer Nature
- p. 55-64
A Velocity Analysis Framework for 2-DOF Above-Knee Prosthetic Legs via DH Based Jacobian Kinematics
- Open Access
End-Effector-Based Robots for Post-Stroke Rehabilitation of Proximal Arm Joints: A Literature Review
Experiencing weakness or paralysis on one side of the body is a common consequence of stroke, with approximately 8 out of 10 patients experiencing some degree of Hemiparesis. Rehabilitation through physiotherapy and occupational therapy is one of the primary methods used to alleviate these conditions. However, physiotherapy, provided by a therapist, is not always readily available. Rehabilitation robots have been studied as alternatives and supplements to conventional therapy. These robots, based on their interaction with the user, can be categorized as end-effector and exoskeleton-based robots. This work aims to examine end-effector rehabilitation robots targeting hemiplegic arm’s proximal joints (shoulder and elbow) for post-stroke recovery. Additionally, we analyze their mechanical design, training modes, user interfaces, and clinical outcomes, highlighting trends and gaps in these systems. Furthermore, we suggest design considerations for home-based therapy and future integration with tele-rehabilitation, based on our findings. This review uniquely focuses on end-effector robots for proximal joints, synthesizing design trends and clinical evidence to guide future development.
Open AccessEnd-Effector-Based Robots for Post-Stroke Rehabilitation of Proximal Arm Joints: A Literature Review
Experiencing weakness or paralysis on one side of the body is a common consequence of stroke, with approximately 8 out of 10 patients experiencing some degree of Hemiparesis. Rehabilitation through physiotherapy and occupational therapy is one of the primary methods used to alleviate these conditions. However, physiotherapy, provided by a therapist, is not always readily available. Rehabilitation robots have been studied as alternatives and supplements to conventional therapy. These robots, based on their interaction with the user, can be categorized as end-effector and exoskeleton-based robots. This work aims to examine end-effector rehabilitation robots targeting hemiplegic arm’s proximal joints (shoulder and elbow) for post-stroke recovery. Additionally, we analyze their mechanical design, training modes, user interfaces, and clinical outcomes, highlighting trends and gaps in these systems. Furthermore, we suggest design considerations for home-based therapy and future integration with tele-rehabilitation, based on our findings. This review uniquely focuses on end-effector robots for proximal joints, synthesizing design trends and clinical evidence to guide future development.
- Open Access
- 7 May 2024
- Published by University of South Florida Libraries
Robotic Accessibility Assistant (RAA)
Individuals with muscular dystrophy and spinal cord injuries often experience upper-limb disabilities and rely on Power wheelchairs for their mobility. While these wheelchairs enhance their quality of life, they do not fully address challenges in activities of daily living (ADL). Specifically, the stiffening of tendons and ligaments in hand joints makes it difficult for individuals to perform accessibility tasks such as pressing elevator buttons and scanning access cards. This paper presents an affordable, simple, and convenient solution to these challenges. The proposed robotic arm offers several unique features. Equipped with a 4-DOF system (3 revolute joints and 1 prismatic joint), it enables easy 3D navigation, controlled via an assistive joystick. Its electrical system uses a Raspberry Pi as the primary microcontroller and an Arduino for joystick input. The four interchangeable end-effectors include a card holder, a ballpoint for pushing buttons, a hook, and a 1 DOF gripper. Other features include 3D printed covers, easy assembly, and quick attachment/detachment. Additionally, this accessory meets National ADA Standards for accessible design, ensuring the wheelchair adheres to a width clearance of 32 inches.
- 7 May 2024
- Published by University of South Florida Libraries
Open AccessRobotic Accessibility Assistant (RAA)
Individuals with muscular dystrophy and spinal cord injuries often experience upper-limb disabilities and rely on Power wheelchairs for their mobility. While these wheelchairs enhance their quality of life, they do not fully address challenges in activities of daily living (ADL). Specifically, the stiffening of tendons and ligaments in hand joints makes it difficult for individuals to perform accessibility tasks such as pressing elevator buttons and scanning access cards. This paper presents an affordable, simple, and convenient solution to these challenges. The proposed robotic arm offers several unique features. Equipped with a 4-DOF system (3 revolute joints and 1 prismatic joint), it enables easy 3D navigation, controlled via an assistive joystick. Its electrical system uses a Raspberry Pi as the primary microcontroller and an Arduino for joystick input. The four interchangeable end-effectors include a card holder, a ballpoint for pushing buttons, a hook, and a 1 DOF gripper. Other features include 3D printed covers, easy assembly, and quick attachment/detachment. Additionally, this accessory meets National ADA Standards for accessible design, ensuring the wheelchair adheres to a width clearance of 32 inches.
- Open Access
LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping
Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera's extrinsic parameters at those viewpoints, and 3D CAD models of objects. The first step involves a standard deep learning backbone (FCN ResNet) to estimate the object label, semantic segmentation, and a coarse estimate of the object pose with respect to the camera. Our novelty is using a refinement module that starts from the coarse pose estimate and refines it by optimisation through differentiable rendering. This is a purely vision-based approach that avoids the need for other information such as point cloud or depth images. We evaluate our object pose estimation approach on the ShapeNet dataset and show improvements over the state of the art. We also show that the estimated object pose results in 99.65% grasp accuracy with the ground truth grasp candidates on the Object Clutter Indoor Dataset (OCID) Grasp dataset, as computed using standard practice.
Open AccessLocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping
Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera's extrinsic parameters at those viewpoints, and 3D CAD models of objects. The first step involves a standard deep learning backbone (FCN ResNet) to estimate the object label, semantic segmentation, and a coarse estimate of the object pose with respect to the camera. Our novelty is using a refinement module that starts from the coarse pose estimate and refines it by optimisation through differentiable rendering. This is a purely vision-based approach that avoids the need for other information such as point cloud or depth images. We evaluate our object pose estimation approach on the ShapeNet dataset and show improvements over the state of the art. We also show that the estimated object pose results in 99.65% grasp accuracy with the ground truth grasp candidates on the Object Clutter Indoor Dataset (OCID) Grasp dataset, as computed using standard practice.
- Open Access
CARRT—Motion Capture Data for Robotic Human Upper Body Model
In recent years, researchers have focused on analyzing humans’ daily living activities to study various performance metrics that humans subconsciously optimize while performing a particular task. In order to recreate these motions in robotic structures based on the human model, researchers developed a framework for robot motion planning which is able to use various optimization methods to replicate similar motions demonstrated by humans. As part of this process, it will be necessary to record the motions data of the human body and the objects involved in order to provide all the essential information for motion planning. This paper aims to provide a dataset of human motion performing activities of daily living that consists of detailed and accurate human whole-body motion data collected using a Vicon motion capture system. The data have been utilized to generate a subject-specific full-body model within OpenSim. Additionally, it facilitated the computation of joint angles within the OpenSim framework, which can subsequently be applied to the subject-specific robotic model developed MATLAB framework. The dataset comprises nine daily living activities and eight Range of Motion activities performed by ten healthy participants and with two repetitions of each variation of one action, resulting in 340 demonstrations of all the actions. A whole-body human motion database is made available to the public at the Center for Assistive, Rehabilitation, and Robotics Technologies (CARRT)-Motion Capture Data for Robotic Human Upper Body Model, which consists of raw motion data in .c3d format, motion data in .trc format for the OpenSim model, as well as post-processed motion data for the MATLAB-based model.
Open AccessCARRT—Motion Capture Data for Robotic Human Upper Body Model
In recent years, researchers have focused on analyzing humans’ daily living activities to study various performance metrics that humans subconsciously optimize while performing a particular task. In order to recreate these motions in robotic structures based on the human model, researchers developed a framework for robot motion planning which is able to use various optimization methods to replicate similar motions demonstrated by humans. As part of this process, it will be necessary to record the motions data of the human body and the objects involved in order to provide all the essential information for motion planning. This paper aims to provide a dataset of human motion performing activities of daily living that consists of detailed and accurate human whole-body motion data collected using a Vicon motion capture system. The data have been utilized to generate a subject-specific full-body model within OpenSim. Additionally, it facilitated the computation of joint angles within the OpenSim framework, which can subsequently be applied to the subject-specific robotic model developed MATLAB framework. The dataset comprises nine daily living activities and eight Range of Motion activities performed by ten healthy participants and with two repetitions of each variation of one action, resulting in 340 demonstrations of all the actions. A whole-body human motion database is made available to the public at the Center for Assistive, Rehabilitation, and Robotics Technologies (CARRT)-Motion Capture Data for Robotic Human Upper Body Model, which consists of raw motion data in .c3d format, motion data in .trc format for the OpenSim model, as well as post-processed motion data for the MATLAB-based model.
- Open Access
Biomimetic Approaches for Human Arm Motion Generation: Literature Review and Future Directions
In recent years, numerous studies have been conducted to analyze how humans subconsciously optimize various performance criteria while performing a particular task, which has led to the development of robots that are capable of performing tasks with a similar level of efficiency as humans. The complexity of the human body has led researchers to create a framework for robot motion planning to recreate those motions in robotic systems using various redundancy resolution methods. This study conducts a thorough analysis of the relevant literature to provide a detailed exploration of the different redundancy resolution methodologies used in motion generation for mimicking human motion. The studies are investigated and categorized according to the study methodology and various redundancy resolution methods. An examination of the literature revealed a strong trend toward formulating intrinsic strategies that govern human movement through machine learning and artificial intelligence. Subsequently, the paper critically evaluates the existing approaches and highlights their limitations. It also identifies the potential research areas that hold promise for future investigations.
Open AccessBiomimetic Approaches for Human Arm Motion Generation: Literature Review and Future Directions
In recent years, numerous studies have been conducted to analyze how humans subconsciously optimize various performance criteria while performing a particular task, which has led to the development of robots that are capable of performing tasks with a similar level of efficiency as humans. The complexity of the human body has led researchers to create a framework for robot motion planning to recreate those motions in robotic systems using various redundancy resolution methods. This study conducts a thorough analysis of the relevant literature to provide a detailed exploration of the different redundancy resolution methodologies used in motion generation for mimicking human motion. The studies are investigated and categorized according to the study methodology and various redundancy resolution methods. An examination of the literature revealed a strong trend toward formulating intrinsic strategies that govern human movement through machine learning and artificial intelligence. Subsequently, the paper critically evaluates the existing approaches and highlights their limitations. It also identifies the potential research areas that hold promise for future investigations.
- 19 February 2023
- Published by Springer Nature
- p. 699-711
LocaliseBot: Multi-view 3D Object Localisation with Differentiable Rendering for Robot Grasping
- 19 February 2023
- Published by Springer Nature
- p. 699-711
LocaliseBot: Multi-view 3D Object Localisation with Differentiable Rendering for Robot Grasping
- 13 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 6907-6914
Formulation and Validation of an Intuitive Quality Measure for Antipodal Grasp Pose Evaluation
This letter describes a novel grasp quality measure that we developed for evaluating antipodal grasp poses in real-time. To quantify the grasp quality, we compute a set of object movement features from analyzing the interaction between the gripper and the object's projections in the image space. The normalization and weights of the features are tuned to make practical and intuitive grasp quality predictions. To evaluate our grasp quality measure, we conducted a real robot grasping experiment with 1000 robot grasp trials on 10 household objects to examine the relationship between our grasp scores and the actual robot grasping results. The results show that the average grasp success rate increases, and the average amount of undesired object movement decreases as the calculated grasp score increases. We achieved a 100% grasp success rate from 100 grasps of the 10 objects when using our grasp quality measure in planning top quality grasps. In addition, we compared our quality measure with the Q measure and deep learning-based quality measures.
- 13 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (4) , 6907-6914
Formulation and Validation of an Intuitive Quality Measure for Antipodal Grasp Pose Evaluation
This letter describes a novel grasp quality measure that we developed for evaluating antipodal grasp poses in real-time. To quantify the grasp quality, we compute a set of object movement features from analyzing the interaction between the gripper and the object's projections in the image space. The normalization and weights of the features are tuned to make practical and intuitive grasp quality predictions. To evaluate our grasp quality measure, we conducted a real robot grasping experiment with 1000 robot grasp trials on 10 household objects to examine the relationship between our grasp scores and the actual robot grasping results. The results show that the average grasp success rate increases, and the average amount of undesired object movement decreases as the calculated grasp score increases. We achieved a 100% grasp success rate from 100 grasps of the 10 objects when using our grasp quality measure in planning top quality grasps. In addition, we compared our quality measure with the Q measure and deep learning-based quality measures.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (4) , 5835-5841
Development of Smartphone-Based Human-Robot Interfaces for Individuals With Disabilities
Persons with disabilities often rely on caregivers or family members to assist in their daily living activities. Robotic assistants can provide an alternative solution if intuitive user interfaces are designed for simple operations. Current human-robot interfaces are still far from being able to operate in an intuitive way when used for complex activities of daily living (ADL). In this era of smartphones that are packed with sensors, such as accelerometers, gyroscopes and a precise touch screen, robot controls can be interfaced with smartphones to capture the user's intended operation of the robot assistant. In this paper, we review the current popular human-robot interfaces, and we present three novel human-robot smartphone-based interfaces to operate a robotic arm for assisting persons with disabilities in their ADL tasks. Useful smartphone data, including 3 dimensional orientation and 2 dimensional touchscreen positions, are used as control variables to the robot motion in Cartesian teleoperation. In this paper, we present the three control interfaces, their implementation on a smartphone to control a robotic arm, and a comparison between the results on using the three interfaces for three different ADL tasks. The developed interfaces provide intuitiveness, low cost, and environmental adaptability.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (4) , 5835-5841
Development of Smartphone-Based Human-Robot Interfaces for Individuals With Disabilities
Persons with disabilities often rely on caregivers or family members to assist in their daily living activities. Robotic assistants can provide an alternative solution if intuitive user interfaces are designed for simple operations. Current human-robot interfaces are still far from being able to operate in an intuitive way when used for complex activities of daily living (ADL). In this era of smartphones that are packed with sensors, such as accelerometers, gyroscopes and a precise touch screen, robot controls can be interfaced with smartphones to capture the user's intended operation of the robot assistant. In this paper, we review the current popular human-robot interfaces, and we present three novel human-robot smartphone-based interfaces to operate a robotic arm for assisting persons with disabilities in their ADL tasks. Useful smartphone data, including 3 dimensional orientation and 2 dimensional touchscreen positions, are used as control variables to the robot motion in Cartesian teleoperation. In this paper, we present the three control interfaces, their implementation on a smartphone to control a robotic arm, and a comparison between the results on using the three interfaces for three different ADL tasks. The developed interfaces provide intuitiveness, low cost, and environmental adaptability.