Prof. Hao Xu Profile

Prof. Hao Xu

Assistant Professor at Univ of Nevada Reno

SPIE Involvement:

Conference Program Committee | Author

Publications (16)

Proceedings Article | 6 June 2024 Presentation + Paper

Enhanced robot state estimation using physics-informed neural networks and multimodal proprioceptive data

Yuqing Liu, Yajie Bao, Peng Cheng, Dan Shen, Genshe Chen, Hao Xu

Proceedings Volume 13062, 130620J (2024) https://doi.org/10.1117/12.3022666

KEYWORDS: Sensors, Kinematics, Neural networks, Satellite navigation systems, Matrices, Calibration, Signal filtering, Environmental sensing, Gyroscopes, Tunable filters

Read Abstract +

In this study, we introduce an innovative Robot State Estimation (RSE) methodology incorporating a learning-based contact estimation framework for legged robots, which obviates the need for external physical contact sensors. This approach integrates multimodal proprioceptive sensory data, employing a Physics-Informed Neural Network (PINN) in conjunction with an Unscented Kalman Filter (UKF) to enhance the state estimation process. The primary objective of this RSE technique is to calibrate the Inertial Measurement Unit (IMU) effectively and furnish a detailed representation of the robot’s dynamic state. Our methodology exploits the PINN to mitigate IMU drift issues by imposing constraints on the loss function via Ordinary Differential Equations (ODEs). The advantages of utilizing a contact estimator based on proprioceptive sensory data are multifold. Unlike vision-based state estimators, our proprioceptive approach is immune to visual impairments such as obscured or ambiguous environments. Moreover, it circumvents the necessity for dedicated contact sensors—components not universally present on robotic platforms and challenging to integrate without substantial hardware modifications. The contact estimator within our network is trained to discern contact events across various terrains, thereby facilitating resilient proprioceptive odometry. This enables the contact-aided invariant Kalman Filter to produce precise odometric trajectories. Subsequently, the UKF algorithm estimates the robot’s three-dimensional attitude, velocity, and position. Experimental validation of our proposed PINN-based method illustrates its capacity to assimilate data from multiple sensors, effectively reducing the influence of sensor biases by enforcing ODE constraints, all while preserving intrinsic sensor characteristics. When juxtaposed with the employment of the UKF algorithm in isolation, our integrated RSE model demonstrates superior performance in state estimation. This enhanced capability automatically reduces sensor drift impacts during operational deployment, rendering our proposed solution applicable to real-world scenarios.

Proceedings Article | 14 June 2023 Presentation + Paper

Intelligent design for quadruped robot on a dynamic flexible surface with an active spine

Yuqing Liu, Sanket Lokhande, Hao Xu

Proceedings Volume 12549, 1254903 (2023) https://doi.org/10.1117/12.2664154

KEYWORDS: Spine, Reservoir computing, Design and modelling, Education and training, Sensors, Robotics, Feedback loops, Systems modeling

Read Abstract +

Proceedings Article | 14 June 2023 Presentation + Paper

An intelligent mission-oriented and situation aware quadruped robot: a novel embodied explainable AI approach

Sanket Lokhande, Joseph Dailey, Yuqing Liu, Samantha Connolly, Hao Xu

Proceedings Volume 12549, 125490E (2023) https://doi.org/10.1117/12.2664019

KEYWORDS: Machine learning, Deep learning, Switching, Neural networks, Artificial intelligence

Read Abstract +

Quadruped locomotion and gait patterns as trotting, galloping, trot running has been investigated and applied to a variety of existing quadruped robots such as Big Dog from Boston Dynamics, A1 Robot dog from Unitree. Most of these studies are based either on biology inspired gaits or the best possible locomotion that can be performed by the individual robot with its pre-set mechanics and its availability of the degree of freedoms. While these are already available as their basic modes, a wide number of researchers are investigating locomotion via deep neural nets. These are making headlines in the research community for efficiency of use, and yet the explainability is lacking in most cases. Just like a Large Language Model might give spurious results here and there for basic common sense questions, these deep neural nets also make errors with unknown interpretability to the inputs. Regarding training, they require careful tuning of hyperparameters and training with a number of parameters unknown to user predictions. For example, on the field we might have a terrain which is flat for a certain length, in addition to a rocky climb, followed by a slippery slope. The combinations are as many as possible and the existing state of the art is heavily depending on human intervention and training predictions to handle the change of modes of the gait patterns that can fit into the terrain underneath. In this paper, we develop a novel embodied explainable machine learning algorithm which can help minimize the training as well as human intervention when autonomous operations are required. Specifically, we utilize the Markov Decision Process (MDP) along with rules set forth by DARPA in the Explainable AI (XAI) research. The XAI research enables us to generate textual explanations of the behavior by utilizing the MDP and reinforcement learning to generate mission oriented and situation aware cost functions along with the ones which are already pre-programmed. We validate our hypothesis in real hardware across different conditions.

Proceedings Article | 14 June 2023 Presentation + Paper

Intelligent collaborative sensing for detection and removal of small distributed space debris

Joseph Dailey, Samantha Connolly, Sanket Lokhande, Hao Xu

Proceedings Volume 12546, 125460I (2023) https://doi.org/10.1117/12.2675494

KEYWORDS: Sensors, Satellites, Data fusion, Radar, Neural networks, Telecommunications, Signal filtering, Radar sensor technology

Read Abstract +

Proceedings Article | 14 June 2023 Presentation + Paper

A novel explainable AI-based situation recognition for autonomous robots with partial unlabeled data

Sanket Lokhande, Joseph Dailey, Yuqing Liu, Samantha Connolly, Hao Xu

Proceedings Volume 12546, 1254606 (2023) https://doi.org/10.1117/12.2664016

KEYWORDS: Machine learning, Data modeling, Robots, Switching, Artificial intelligence, Decision making

Read Abstract +

Proceedings Article | 3 June 2022 Presentation + Paper

Hybrid learning-based online high-accuracy pedestrian dead reckoning navigation system with AI-on-a-chip

Sanket Lokhande, Qingliang Zhao, Frank Tucker, Hao Xu, Nichole Sullivan, Genshe Chen

Proceedings Volume 12121, 1212105 (2022) https://doi.org/10.1117/12.2623038

KEYWORDS: Navigation systems, Algorithm development, Evolutionary algorithms, Detection and tracking algorithms, Data modeling, Sensors, Error analysis, Target recognition, Numerical simulations, Neural networks

Read Abstract +

Proceedings Article | 27 April 2020 Presentation

Multi-autonomous robot enhanced mobile ad-hoc network under uncertain and vulnerable environment (Conference Presentation)

Ming Feng, Hao Xu

Proceedings Volume 11426, 1142603 (2020) https://doi.org/10.1117/12.2556226

KEYWORDS: Algorithm development, Computer aided design, Computer simulations, Social networks, Mobile communications, Virtual reality, Mixed reality

Read Abstract +

Proceedings Article | 27 April 2020 Presentation

Switching deep reinforcement learning based intelligent online decision making for self-organizing autonomous systems under unstructured environment (Conference Presentation)

Zejian Zhou, Hao Xu

Proceedings Volume 11425, 114250K (2020) https://doi.org/10.1117/12.2556225

KEYWORDS: Switching, Neural networks, Tolerancing, Computer simulations

Read Abstract +

Proceedings Article | 27 April 2020 Presentation

Deep reinforcement learning based intelligent decision making for multi-player sequential game with uncertain irrational players (Conference Presentation)

Zejian Zhou, Hao Xu

Proceedings Volume 11422, 114220H (2020) https://doi.org/10.1117/12.2556224

KEYWORDS: Robots, Sensors, Dynamical systems, Numerical simulations

Read Abstract +

Proceedings Article | 27 April 2020 Presentation

Mean field game and decentralized intelligent adaptive pursuit evasion strategy for massive multi-agent system under uncertain environment (Conference Presentation)

Zejian Zhou, Hao Xu

Proceedings Volume 11413, 114131F (2020) https://doi.org/10.1117/12.2556222

KEYWORDS: Strategic intelligence, Neural networks, Telecommunications, Numerical simulations

Read Abstract +

Proceedings Article | 14 May 2018 Presentation

Mission critical decentralized resilient and intelligent control for networked heterogeneous unmanned autonomous systems (Conference Presentation)

Hao Xu

Proceedings Volume 10643, 106430I (2018) https://doi.org/10.1117/12.2304718

KEYWORDS: Control systems, Telecommunications, Algorithm development, Pollution control

Read Abstract +

Proceedings Article | 14 May 2018 Presentation

Brain emotional learning-based intelligent path planning and coordination control of networked unmanned autonomous systems (Conference Presentation)

Hao Xu

Proceedings Volume 10640, 106400I (2018) https://doi.org/10.1117/12.2304715

KEYWORDS: Brain, Control systems, Dynamical systems, Systems modeling, Limbic system

Read Abstract +

Proceedings Article | 5 May 2017 Presentation + Paper

Model-free adaptive controller for autonomous aerial transportation of suspended loads with unknown characteristics

Ricardo A. Barron-Gomez, Luis E. Ramos-Velasco, Eduardo S. Espinoza-Quesada, Hao Xu, Luis Rodolfo Garcia Carrillo

Proceedings Volume 10195, 1019512 (2017) https://doi.org/10.1117/12.2262924

KEYWORDS: Systems modeling, Warfare, Neural networks, Wavelets, Mathematical modeling, Control systems, System identification, Navigation systems, Error analysis, Evolutionary algorithms

Read Abstract +

Due to the highly uncertain and dynamic nature of military conflict and planetary exploration missions, enabling aerial and terrestrial unmanned autonomous systems (UAS) to gracefully adapt to mission and environmental changes is a very challenging task. In particular, the United States Army, Air Force, Navy, and NASA have recently shown interest in the task of load transportation by means of UAS, which rely heavily on the knowledge of both the UAS model and the load dynamics to function. Most of the currently available autopilot systems for UAS were built without suspended load transportation capabilities and are thus not appropriate, for example, to assist soldiers or planetary explorers in the tasks of carrying and deploying supplies, transporting injured people, or warfare. This research provides knowledge to the problem of autonomous suspended load transportation, attending national agencies expectations that UAS will perform in a reliable manner even in the challenging situation when loads of uncertain characteristics are transported and deployed, which heavily modify the UAS dynamic during the execution of the task. This work presents a novel model-free adaptive wavenet PID (AWPID)-based controller for enabling aerial UAS to transport cable suspended loads of unknown characteristics. In order to accomplish this goal, a control design is presented which enables the UAS to perform a trajectory tracking task, based solely on the knowledge of the UAS position. The methodology proposes a novel structure, which identifies inverse error dynamics using a radial basis neural network with daughter Mexican hat wavelets activation function. A real-time load transportation mission consisting of a multi-rotorcraft UAS carrying a cable suspended load of unknown characteristics validates the effectiveness of the trajectory tracking control strategy, showing smooth control signals even when the mathematical model of the aerial UAS and load dynamics are not known.

Proceedings Article | 5 May 2017 Presentation + Paper

Advanced wireless mobile collaborative sensing network for tactical and strategic missions

Hao Xu

Proceedings Volume 10184, 101840R (2017) https://doi.org/10.1117/12.2262963

KEYWORDS: Mobile robots, Unmanned aerial vehicles, Infrared sensors, Sensors, Telecommunications, Environmental sensing, Sensor networks, Unmanned ground vehicles, Sensing systems, Infrared cameras, Antennas, Algorithm development, Wireless communications, Control systems, Near field

Read Abstract +

Proceedings Article | 5 May 2017 Presentation + Paper

Fast reinforcement learning based distributed optimal flocking control and network co-design for uncertain networked multi-UAV system

Hao Xu, L. R. G. Carrillo

Proceedings Volume 10195, 1019511 (2017) https://doi.org/10.1117/12.2262877

KEYWORDS: Control systems, Computer programming, Telecommunications, Algorithm development, Defense technologies, Systems modeling, Mathematical modeling, Network architectures, Earthquakes, Error analysis, Unmanned aerial vehicles, Nickel, Stochastic processes, Wireless communications

Read Abstract +

Proceedings Article | 1 May 2017 Presentation + Paper

Advanced Doppler radar physiological sensing technique for drone detection

Ji Hwan Yoon, Hao Xu, Luis Garcia Carrillo

Proceedings Volume 10188, 101880S (2017) https://doi.org/10.1117/12.2262758

KEYWORDS: Sensors, K band, Target detection, Chest, Antennas, Unmanned aerial vehicles, Doppler effect, Radar, Advanced radar, Vital signs, Defense technologies, Biometrics, Tissues, Data processing

Read Abstract +

Showing 5 of 16 publications

Conference Committee Involvement (1)

Sensors and Systems for Space Applications XVIII

16 April 2025 | Orlando, Florida, United States

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years