A5070869235- Real-Time Systems Scheduling
- Autonomous Vehicle Technology and Safety
- Embedded Systems Design Techniques
- Adversarial Robustness in Machine Learning
- Vehicular Ad Hoc Networks (VANETs)
- Anomaly Detection Techniques and Applications
- Formal Methods in Verification
- Fault Detection and Control Systems
- Distributed systems and fault tolerance
- Radiation Effects in Electronics
- Software System Performance and Reliability
- Traffic control and management
- GNSS positioning and interference
- Advanced Malware Detection Techniques
- Indoor and Outdoor Localization Technologies
- Smart Grid Security and Resilience
- Advanced Software Engineering Methodologies
- Petri Nets in System Modeling
- Real-time simulation and control systems
- Cardiac Arrest and Resuscitation
- Target Tracking and Data Fusion in Sensor Networks
Huawei Technologies (China)
2024
Northwestern University
2018-2021
University of California, Riverside
2016-2017
Indoor positioning is a thriving research area which slowly gaining market momentum. Its applications are mostly customised, ad hoc installations; ubiquitous analogous to GNSS for outdoors not available because of the lack generic platforms, widely accepted standards and interoperability protocols. In this context, Positioning Navigation (IPIN) competition only long-term, technically sound initiative monitor state art real systems by measuring their performance in realistic environment. Most...
With the rapid advancement of autonomous driving and vehicular communication technology, intelligent intersection management has shown great promise in improving transportation efficiency. In a typical intersection, an manager communicates with vehicles wirelessly schedules their crossing intersection. Previous system designs, however, do not address possible delays due to network congestion or security attacks, could lead unsafe deadlocked systems. this work, we propose delay- tolerant...
To support emerging applications in autonomous and semi-autonomous driving, next-generation automotive systems will be equipped with an increasing number of heterogeneous components (sensors, actuators computation units connected through various buses), have to process a high volume data percept the environment accurately efficiently. Challenges for such include system integration, prediction, verification validation. In this work, we propose architecture modeling exploration framework...
Future autonomous systems will employ sophisticated machine learning techniques for the sensing and perception of surroundings making corresponding decisions planning, control, other actions. They often operate in highly dynamic, uncertain challenging environment, need to meet stringent timing, resource, mission requirements. In particular, it is critical yet very ensure safety these systems, given uncertainties system inputs, constant disturbances on operations, lack analyzability many...
Future autonomous systems will employ complex sensing, computation, and communication components for their perception, planning, control, coordination, could operate in highly dynamic uncertain environment with safety security assurance. To realize this vision, we have to better understand address the challenges from "unknowns" - unexpected disturbances component faults, environmental interference, malicious attacks, as well inherent uncertainties system inputs, model inaccuracies, machine...
Next-generation autonomous and semi-autonomous vehicles will not only precept the environment with their own sensors, but also communicate other surrounding infrastructures for vehicle safety transportation efficiency. The design, analysis validation of various vehicle-to-vehicle (V2V) vehicle-to-infrastructure (V2I) applications involve multiple layers, from V2V/V2I communication networks down to software hardware individual vehicles, concern stringent requirements on metrics such as...
For many embedded systems, such as automotive electronic security has become a pressing challenge. Limited resources and tight timing constraints often make it difficult to apply even lightweight authentication intrusion detection schemes, especially when retrofitting existing designs. Moreover, traditional hard deadline assumption is insufficient describe control tasks that have certain degrees of robustness can tolerate some misses while satisfying functional properties stability. In this...
Connected vehicle applications such as autonomous intersections and intelligent traffic signals have shown great promises in improving transportation safety efficiency. However, security is a major concern these systems, vehicles surrounding infrastructures communicate through ad-hoc networks. In this paper, we will first review vulnerabilities connected applications. We then introduce discuss some of the defense mechanisms at network system levels, including (1) Security Credential...
This article presents multiple cross-layer methods to ensure security as well functional correctness of automotive systems. These approaches tie together abstraction layers, going all the way from vehicular networks responsible for vehicle-to-vehicle and vehicle-to-infrastructure communication, in-vehicle hardware/software architectures.
Many safety-critical real-time systems operate under harsh environment and are subject to soft errors caused by transient or intermittent faults. It is critical yet often very challenging apply fault tolerance techniques in these systems, due resource limitations stringent constraints on timing functionality. In this work, we leverage the concept of weakly-hard constraints, which allows task deadline misses a bounded manner, improve system's capability accommodate while ensuring functional...
In the development of advanced driver-assistance systems (ADAS) and autonomous vehicles, machine learning techniques that are based on deep neural networks (DNNs) have been widely used for vehicle perception. These offer significant improvement average perception accuracy over traditional methods, however shown to be susceptible adversarial attacks, where small perturbations in input may cause errors results lead system failure. Most prior works addressing such attacks focus only sensing...
With rapid advancement of advanced driver assistance systems (ADAS) and autonomous driving functions, modern vehicles have become ever more intelligent than before. Sophisticated machine learning techniques being developed for vehicle perception, planning control. However, this also brings significant challenges to the design, implementation validation automotive systems, stemming from fast-growing functional complexity, adoption architectural components such as multicore CPUs GPUs, dynamic...
Machine learning techniques, particularly those based on deep neural networks (DNNs), are widely adopted in the development of advanced driver-assistance systems (ADAS) and autonomous vehicles.While providing significant improvement over traditional methods average performance, usage DNNs also presents great challenges to system safety, especially given uncertainty surrounding environment, disturbance operations, current lack methodologies for predicting DNN behavior.In particular,...
Increasingly more software-based applications are being developed and deployed in modern vehicles. As a result, the extensibility of system design has become an important issue order to accommodate future update existing ones on one hand reduce effort cost re-design, test validation other. In this paper, we discuss extensibility-driven automotive E/E architecture. We explain motivation for such objective definition metric methods under two different setting, namely based CAN bus FlexRay bus....
The design of automotive electronic systems needs to address a variety important objectives, including safety, performance, fault tolerance, reliability, security, extensibility, etc. To obtain feasible design, timing constraints must be satisfied and latencies certain functional paths should not exceed their deadlines. From functionality perspective, soft errors caused by transient or intermittent faults need detected recovered with tolerance techniques. Moreover, during the lifetime...
With growing system complexity and closer cyber-physical interaction, there are increasingly stronger dependencies between different function architecture layers in automotive systems. This paper first introduces several cross-layer approaches we developed the past for holistically addressing multiple design of individual vehicles connected vehicle applications; then presents a new methodology based on weakly-hard paradigm leveraging scheduling flexibility layer to improve performance at...
In the development of advanced driver-assistance systems (ADAS) and autonomous vehicles, machine learning techniques that are based on deep neural networks (DNNs) have been widely used for vehicle perception. These offer significant improvement average perception accuracy over traditional methods, however, shown to be susceptible adversarial attacks, where small perturbations in input may cause errors results lead system failure. Most prior works addressing such attacks focus only sensing...