Hao Su

Bio: Hao Su is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 57, co-authored 302 publications receiving 55902 citations. Previous affiliations of Hao Su include Philips & Jiangxi University of Science and Technology.

Quasi-Direct Drive Actuation for a Lightweight Hip Exoskeleton With High Backdrivability and High Bandwidth

Abstract: High-performance actuators are crucial to enable mechanical versatility of wearable robots, which are required to be lightweight, highly backdrivable, and with high bandwidth. State-of-the-art actuators, e.g., series elastic actuators, have to compromise bandwidth to improve compliance (i.e., backdrivability). In this article, we describe the design and human–robot interaction modeling of a portable hip exoskeleton based on our custom quasi-direct drive actuation (i.e., a high torque density motor with low ratio gear). We also present a model-based performance benchmark comparison of representative actuators in terms of torque capability, control bandwidth, backdrivability, and force tracking accuracy. This article aims to corroborate the underlying philosophy of “design for control,” namely meticulous robot design can simplify control algorithms while ensuring high performance. Following this idea, we create a lightweight bilateral hip exoskeleton to reduce joint loadings during normal activities, including walking and squatting. Experiments indicate that the exoskeleton is able to produce high nominal torque (17.5 Nm), high backdrivability (0.4 Nm backdrive torque), high bandwidth (62.4 Hz), and high control accuracy (1.09 Nm root mean square tracking error, 5.4% of the desired peak torque). Its controller is versatile to assist walking at different speeds and squatting. This article demonstrates performance improvement compared with state-of-the-art exoskeletons.

Design and Control of a High-Torque and Highly Backdrivable Hybrid Soft Exoskeleton for Knee Injury Prevention During Squatting

Abstract: This letter presents design and control innovations of wearable robots that tackle two barriers to widespread adoption of powered exoskeletons: restriction of human movement and versatile control of wearable co-robot systems. First, the proposed high torque density actuation comprised of our customized high-torque density motors and low ratio transmission mechanism significantly reduces the mass of the robot and produces high backdrivability. Second, we derive a biomechanics model-based control that generates assistive torque profile for versatile control of both squat and stoop lifting assistance. The control algorithm detects lifting postures using compact inertial measurement unit (IMU) sensors to generate an assistive profile that is proportional to the human joint torque produced from our model. Experimental results demonstrate that the robot exhibits low mechanical impedance (1.5 Nm backdrive torque) when it is unpowered and 0.5 Nm backdrive torque with zero-torque tracking control. Root mean square (RMS) error of torque tracking is less than 0.29 Nm (1.21% error of 24 Nm peak torque). Compared with squatting without the exoskeleton, the controller reduces 87.5%, 80% and 75% of the three knee extensor muscles (average peak EMG of 3 healthy subjects) during squat with 50% of human joint torque assistance.

A 3-axis optical force/torque sensor for prostate needle placement in Magnetic resonance imaging environments

Abstract: The work presented in this paper has been performed in furtherance of developing an MRI (Magnetic resonance imaging) compatible fiber optical force sensor. In this paper, we discuss the design criteria and sensing principle of this optical sensor for monitoring forces in the 0–20 Newton range with an sub-Newton resolution. This instrumentation enables two degrees-of-freedom (DOF) torque measurement and one DOF force measurement. A novel flexure mechanism is designed and the finite element analysis is performed to aid the optimization of the design parameters. This 3 axis force/torque sensor with this range and resolution is an ideal tool for interventional procedures, e.g. needle biopsy and brachytherapy. The sensor is experimentally investigated and calibrated. Calibration results demonstrate that this sensor is a practical and accurate measurement apparatus.

An affordable compact humanoid robot for autism spectrum disorder interventions in children

Abstract: Autism Spectrum Disorder impacts an ever-increasing number of children. The disorder is marked by social functioning that is characterized by impairment in the use of nonverbal behaviors, failure to develop appropriate peer relationships and lack of social and emotional exchanges. Providing early intervention through the modality of play therapy has been effective in improving behavioral and social outcomes for children with autism. Interacting with humanoid robots that provide simple emotional response and interaction has been shown to improve the communication skills of autistic children. In particular, early intervention and continuous care provide significantly better outcomes. Currently, there are no robots capable of meeting these requirements that are both low-cost and available to families of autistic children for in-home use. This paper proposes the piloting the use of robotics as an improved diagnostic and early intervention tool for autistic children that is affordable, non-threatening, durable, and capable of interacting with an autistic child. This robot has the ability to track the child with its 3 degree of freedom (DOF) eyes and 3-DOF head, open and close its 1-DOF beak and 1-DOF each eyelids, raise its 1-DOF each wings, play sound, and record sound. These attributes will give it the ability to be used for the diagnosis and treatment of autism. As part of this project, the robot and the electronic and control software have been developed, and integrating semi-autonomous interaction, teleoperation from a remote healthcare provider and initiating trials with children in a local clinic are in progress.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.