Madhur Behl
Associate Professor, Computer Science, Systems and Information Engineering
Cyber-Physical Systems, Link Lab
Cavalier Autonomous Racing
Research Website
Cavalier Autonomous Racing
UVA F1/10 Autonomous Racing
Principles of Modeling for Cyber-Physical Systems
UVA Engineering Link Lab
Learning In Robotics
Google Scholar
Course Catalog
About
Dr. Madhur Behl is an associate professor in the departments of Computer Science, and Systems and Information Engineering, and a member of the Cyber-Physical Systems Link Lab at the University of Virginia. He conducts research at the confluence of Machine Learning, Predictive Control, and Artificial Intelligence with applications in Cyber-Physical Systems, Autonomous Systems, Robotics, and Smart Cities. Examples include: fully autonomous racing at the limits of control (Agile Autonomy), safety of autonomous vehicles (Safe Autonomy), building world models for robotics, data predictive control for flooding in coastal cities, and AI for building energy optimization.
He is the team principal of the University of Virginia's Cavalier Autonomous Racing team - racing full-scale, fully autonomous Indy cars (HTTPS://AUTONOMOUSRACING.DEV/). Behl is also the co-founder, organizer, and the race director for the F1/10 (F1tenth) International Autonomous Racing Competitions. He is an Associate Editor for the SAE Journal on Connected and Autonomous Vehciles, and a Guest Editor for the Journal of Field Robotics. He also serves on the on the Academic Advisory Council of the Partners for Automated Vehicle Education (PAVE) campaign, to help promote public understanding about autonomous vehicles and their potential benefits. Dr. Behl is an IEEE Senior Member and the recipient of the National Science Foundation (NSF) CAREER Award (2021).
He received his Ph.D. (2015) and M.S. (2012), in Electrical and Systems Engineering, both from the University of Pennsylvania; and his bachelor's degree (2009) in ECE from PEC University of Technology in India.
Education
Ph.D. University of Pennsylvania, 2015
M.S. University of Pennsylvania, 2012
B.S. PEC University of Technology, India, 2009
"Making things go, where they need to go - autonomously !"
Research Interests
Robotics
Artificial Intelligence
Cyber-Physical Systems
Autonomous Systems
Smart Buildings/Cities
Internet of Things
Selected Publications
Varundev SureshBabu and Madhur Behl, "F1tenth.dev - an Open-Source ROS Based F1/10 Autonomous Racing Simulator"
2020 IEEE 16TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE)
Trent Weiss and Madhur Behl "DeepRacing: Parameterized Trajectories for Autonomous Racing"
2020 ARXIV PREPRINT ARXIV:2005.05178
ABS
Trent Weiss, Madhur Behl, "DeepRacing: a framework for autonomous racing"
2020 IEEE DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE), PAGES 1163-1168
ABS
Alexander B Chen, Madhur Behl, Jonathan L Goodall, "Trust me, my neighbors say it's raining outside: ensuring data trustworthiness for crowdsourced weather stations"
2018 PROCEEDINGS OF THE 5TH CONFERENCE ON SYSTEMS FOR BUILT ENVIRONMENTS, PAGES 25-28 [BEST PRESENTATION AWARD]
ABS
Madhur Behl, Achin Jain, and Rahul Mangharam “Data-Driven Modeling, Control and Tools for Cyber- Physical Energy Systems”
ACM/IEEE CONFERENCE ON CYBER-PHYSICAL SYSTEMS, APRIL 2016
ABS
Courses Taught
F1/10 Autonomous Racing - Perception, Planning, and Control for Autonomous Vehicles
SPRING '18,'19,'20
Principles of Modeling for Cyber-Physical Systems
FALL '17,'18,'19,'20
Awards
Best Paper Award: Journal of Water - Open Access
2021
Best Paper Award: International Conference on Intelligent Robotics and Systems (IROS): Workshop on Perception, Learning, and Control for Autonomous Agile Vehicles.
2020
Best Systems Design Award - For ”Autonomous Electric Vehicle Charging System", Systems and Information Engineering Design Symposium (SIEDS).
2019
Best Research Poster Award - 5th ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys)
2018
Best Energy Systems Paper Award - American Control Conference (ACC)
2017
Winner of the 2106 DoE EERE’s Allegheny Region Cleantech University Prize, Carnegie Mellon University, Pittsburgh, USA.
2016
Best Paper Award , for ”Sometimes, Money Does Grow on Trees: Data-Driven Demand Response with DR-Advisor, Internet of Things Session at the Semiconductor Research Corporation’s (SRC) TECHCON, Austin, USA.
2015
Best Demo Award at BuildSys, 4th ACM Workshop On Embedded Systems For Energy-Efficiency In Buildings, Toronto, Canada.
2012
Richard K. Dentel Memorial Prize in Urban Transportation, University of Pennsylvania, Philadelphia, USA.
2011
Winner of the World Embedded Software Contest, Korean Ministry of Knowledge Economy and Electronics and Telecommunications Research Institute (ETRI), Seoul, South Korea.
2010
Featured Grants & Projects
SLES: CRASH - Challenging Reinforcement-learning based Adversarial scenarios for Safety Hardening
National Science Foundation
Autonomous vehicles, with their reliance on learning-enabled components for key operations, promise an exciting future for transportation. Yet, assuring the safety of these vehicles amid unpredictable real-world traffic scenarios filled with 'unknown unknowns' remains a significant hurdle. While on-road testing is essential, it is time-consuming, risky, and insufficient due to the rarity of safety-critical traffic situations. High-fidelity simulations present a promising way to complement these efforts, allowing us to stress-test autonomous vehicles in a myriad of challenging scenarios. This raises key questions: how can we generate rare, but realistic traffic situations in simulation that would truly stress test an autonomous vehicle's safety? Moreover, how can we continuously improve the autonomous vehicle's software to learn from each identified failure? In response, this project offers an innovative approach where we purposefully introduce rare but realistic scenarios in simulation that may cause autonomous vehicles to fail, and then enhance the software to ensure these failures do not reoccur. The implications of the research extends beyond safety improvements, having the potential to redefine industry practices, shape regulatory frameworks for autonomous vehicle safety, and ensure the safe and reliable deployment of autonomous vehicles. The project will develop a new framework, named CRASH - Challenging Reinforcement-learning based Adversarial scenarios for Safety Hardening. CRASH leverages a novel multi-agent adversarial deep reinforcement learning setting to automatically and effectively stress test existing autonomous vehicle software stacks, helping identify potential failures in motion planning. It then enhances the AV's safety performance by improving its ability to avoid repeating these failures and learn from them. Notably, CRASH emphasizes the realistic, plausible, and naturalistic aspects of identified AV failures, mirroring unexpected situations in real-world traffic conditions. The real strength of CRASH is its iterative process, where after each falsification, an improvement simulation leads to continuous enhancement of the autonomous vehicle stack - an approach the team termed safety hardening. This iterative refinement fortifies an AV's safety, allowing it to navigate unexpected traffic situations more efficiently, thereby increasing its resilience. The project provides a pragmatic and reliable pathway to advance the safety testing of autonomous vehicles that rely heavily on learning-enabled components so that they can navigate our roads with an enhanced level of safety and robustness. This research is supported by a partnership between the National Science Foundation and Open Philanthropy.
NSF CAREER: Safe and Agile Autonomous Cyber-Physical Systems
Autonomous Cyber-Physical Systems (CPS), such as self-driving cars, and drones, powered by deep learning and AI based perception, planning, and control algorithms, are forming the basis for significant pieces of our nation’s critical infrastructure, and present direct, and urgent safety-critical challenges. A major limitation with current approaches towards deploying autonomous CPS is in ensuring that the system operates safely, and reliably in situations that do not happen very often under normal operating conditions and are therefore difficult to gather data on. For instance, a self-driving car trained to follow the ‘rules of the road’ will perform well most of the time, but it is the unusual conditions, the edge cases, which pose the hardest safety challenges. This project brings forward an innovative idea – can increasing the agility of an autonomous vehicle improve its safety? This notion is somewhat controversial since agility (like that of race cars) is more frequently associated with decreased safety margins. Motivated by these challenges underlying real-world testing and safety for autonomous vehicles, the goal of this project is to develop the foundations for autonomous cyber-physical systems along two dimensions: agility, safety, and their interplay. The project is centered on (1) increasing agility for AVs by developing new methods for agile motion planning, so they can maneuver at the limits of their handling and control when it matters most to escape potentially unsafe conditions, (2) automated reasoning about uncertain dynamic situations that may occur during autonomous CPS operation, and (3) developing novel methods for automatically generating testing and edge-case scenarios at design time, to explore scenarios under which the autonomous CPS would fail. The proposed methods will be evaluated on scaled autonomous vehicles testbeds, on photorealistic and high-fidelity simulation platforms, and on full scale AV prototypes. The project will also consider not just safety of an unoccupied AV – but one in which passengers may be present. This CAREER project includes designing exciting new courses, and initiatives centered around autonomous racing to engage with research and mentoring for K-12, undergraduate, and graduate students. The project aims to ensure that students cultivate a holistic view of cyber-physical systems and autonomous systems by drawing stronger connections between theory, applications, and hands-on platform development. The project will help enhance the capabilities of autonomous cyber-physical systems and facilitate with their safe deployment.
NSF CRISP Type 2: dMIST: Data-driven Management for Interdependent Stormwater and Transportation Systems
National Science Foundation
The overarching objective of this Critical Resilient Interdependent Infrastructure Systems and Processes (CRISP) research project is to create a novel decision support system denoted dMIST (Data-driven Management for Interdependent Stormwater and Transportation Systems) to improve management of interdependent transportation and stormwater infrastructure systems. dMIST is designed specifically to address the critical problem of recurrent flooding caused by sea level rise and more frequent intense storms. The City of Norfolk, Virginia, a national leader in addressing the sea level rise challenge, will collaborate with the research team and serve as the project testbed. With sea level rise and more frequent intense storms, streets in many cities now flood multiple times per year. Flooding of roadways has cascading impacts to other infrastructure systems that depend on the road network including emergency services. Solving the problem of flooded roadways requires new tools capable of analyzing stormwater, transportation, and other infrastructure as interdependent systems. dMIST will be a recommendation system for assisting municipal decision makers and stakeholders in day-to-day operations to mitigate the short-term impacts of road flooding occurrences. It will also offer decision makers novel ways of testing "what if" scenarios that stretch across interdependent infrastructure systems in order to guide how large investments are used to adapt infrastructure systems to a more resilient future.
Jefferson Trust: Cavalier Autonomous Racing
Awarded Amount: $50,000
The Cavalier Autonomous Racing Club, under the supervision of UVA faculty, will build, develop, program and race an autonomous electric go-kart. Club activity will culminate in a demonstration at the Indianapolis Motor Speedway, home of the Indy 500 race.