Raj Rajkumar
Professor | Carnegie Mellon University
Pittsburgh, PA, UNITED STATES
Raj Rajkumar researches ways to safely bring your vehicle to life with information technology.
Biography
Raj Rajkumar is a professor in the Department of Electrical and Computer Engineering. He is the director of Metro21, Carnegie Mellon University's campus-wide initiative on Smart Cities, and the US Department of Transportation's Mobility21 National University Transportation Center. Rajkumar is thinking of ways to safely bring your vehicle to life with information technology — giving you a car that will know and help you, inform and entertain you, and even take care of itself like a proper traveling companion. That includes connected and autonomous driving, cyber-physical systems, embedded and real-time systems and wired/wireless networking. Rajkumar is exploring the many intricate engineering domains of vehicle operation in a quest for some answers to what's possible in the cars of tomorrow.
Areas of Expertise (4)
Wired/Wireless Networking
Cyber-Physical Systems
Autonomous Driving
Embedded and Real-Time Systems
Media Appearances (5)
Carnegie Mellon gets $20M in federal funds to spark transportation safety initiative
Technical.ly online
2023-05-30
Carnegie Mellon electrical and computer engineering professor Raj Rajkumar said Safety 21 would use research and development to advance tech and policy innovations. “We seek to broaden our impact by ensuring communities have equal access to safety technologies; evaluating energy use and emissions; and supporting domestic commercialization, entrepreneurship and public policy to rally economic strength and global competitiveness,” Rajkumar said.
Tesla closes an office as layoff hits Autopilot jobs, including hourly ones
Reuters online
2022-06-29
"Tesla clearly is in a major cost-cutting mode," said Raj Rajkumar, professor of electrical and computer engineering at Carnegie Mellon University. "This (staff reduction) likely indicates that 2Q 2022 has been pretty rough on the company due to the shutdown in Shanghai, raw material costs and supply chain problems."
The White House is lobbying hard for chip funding that experts say would help Pittsburgh tech firms
90.5 WESA online
2022-04-18
“They cannot actually buy the high-performance computers that they need to basically utilize to train the artificial intelligence to make these products work. So that has clearly hampered the development side of these technologies.” Carnegie Mellon electrical and computer engineering professor Raj Rajkumar said.
Top robotics expert on Uber crash questions whether sensors worked
USA Today online
2018-03-23
"The car's LiDAR (light ranging and detection laser system) should have picked the pedestrian up far before it hit her," says Raj Rajkumar, who leads the autonomous vehicle research team at Carnegie Mellon University.
6 Questions For Carnegie Mellon Autonomous Car Prof
St. Augustine Record online
2015-07-09
Today, the Pittsburgh school is among the world's leaders in autonomous cars. Google's self-driving car chief got his training there. It's doing research for General Motors, and ride-sharing service Uber recently signed on to develop a self-driving vehicle. Raj Rajkumar has helped lead the school's efforts for the past 15 years as a professor of computer and electrical engineering. He also heads a spinoff company that is developing autonomous car software. Here are Rajkumar's answers to questions about the fast-moving technology, edited for length and clarity:
Media
Publications:
Documents:
Photos:
Videos:
Audio/Podcasts:
Industry Expertise (5)
Automotive
Information Technology and Services
Computer Networking
Computer Hardware
Computer Software
Education (2)
Carnegie Mellon University: Ph.D., Electrical and Computer Engineering 1989
Carnegie Mellon University: M.S., Electrical and Computer Engineering
Links (4)
Articles (5)
Characterization of Natural Cellulosic Fiber from Cereus Hildmannianus
Journal of Natural Fibers2021 The research article aims to characterize the physicochemical, morphological, thermal and mechanical properties of novel Cereus Hildmannianus Fibers (CHFs) are reported for the first time in this work. The lower density (1.364 ± 0.026 g/cm3) with high cellulose content of the CHF (58.40 ± 0.56 wt.%) provides better tensile strength 2013–2897 Mpa makes it an attractive option for synthetic fibers. FTIR and X-ray analysis proved that CHF is rich in cellulose content with crystallinity index (46.19%) and crystalline size (28.27 nm), which indicates that the CHF is thermally stable until 285.9°C. Moreover, the large crystalline sizes can reduce the water absorption characteristics. The strong presence of microfibril through scanning electron micrographs assists admirable bonding properties. The results are substantiating the potential of CHFs as reinforcement in composites industries with its significant possessions.
Crashworthiness and comparative analysis of polygonal single and bi-tubular structures under axial loading–experiments and FE modelling
Journal of Theoretical and Applied Mechanics2021 This article aims to present a report of experimental and numerical investigations on crashworthiness characteristics of single and multi-cell/bi-tubular structures. Novel multi--cell/bi-tubular structures are proposed in order to improve the crashworthiness performance, LS-DYNA FE software is applied for the modelling of axial crashing behaviour to validate with experimental results and a good agreement is observed. The KPIs are used to compare various structures and to determine the best performing ones. The investigations reveal that the HMC4 has significantly obvious effects on the structural crashworthiness and improved 515% energy absorption efficiency. Afterward, a parametric study has been carried out for the best energy absorber.
Practical task allocation for software fault-tolerance and its implementation in embedded automotive systems
Real-Time Systems2019 Due to the advent of active safety features and automated driving capabilities, the complexity of embedded computing systems within automobiles continues to increase. Such advanced driver assistance systems (ADAS) are inherently safety-critical and must tolerate failures in any subsystem. However, fault-tolerance in safety-critical systems has been traditionally supported by hardware replication, which is prohibitively expensive in terms of cost, weight, and size for the automotive market. Recent work has studied the use of software-based fault-tolerance techniques that utilize task-level hot and cold standbys to tolerate fail-stop processor and task failures. The benefit of using standbys is maximal when a task and any of its standbys obey the placement constraint of not being co-located on the same processor.
A hybrid algorithm for multi-objective optimization of minimizing makespan and total flow time in permutation flow shop scheduling problems
Information Technology and Control2019 This paper proposes, a multi-objective optimization of minimizing makespan and total flow time of jobs for permutation flow shop scheduling is considered. Bi-objective issues are comprehended by doling out uniform weight to every objective function in view of its preference or determining every competent solutions. In flow shop scheduling environment, many meta-heuristic algorithms have been used to find optimal or near-optimal solutions due to the computational cost of determining exact solutions. This work provides a hybridization of genetic algorithm and simulated annealing algorithm (HGASA) based multi-objective optimization algorithm for flow shop scheduling. HGASA could be a simple and proficient algorithm that is utilized to determine for every single and multi-objective problem in flow shop scheduling shop environment. This algorithm can works simply for realistic manufacturing system applications.
Deformation and energy absorption analysis of simple and multi-cell thin-walled tubes under quasi-static axial crushing
International Journal of Crashworthiness2019 A comparative study of energy absorption characteristics and distortions between simple and multi-cell thin-walled tubes with various geometrics are examined. Energy has to disseminate to avoid damage and harm during collisions. To diminish the misfortunes from collision, thin-walled tubes are utilised to dissipate the kinetic energy by deformation. For this analysis, simple and multi-cell tubes with different sections were made from aluminium (Al 3003) sheet and then they are subjected to quasi-static axial crushing. From the results, the energy absorption capacity of various tubes were compared and it shows that multi-cell tubes have more noteworthy than that of simple tubes. Moreover, hexagonal multi-cell tubes were retained as most prominent for higher specific energy absorption. This type of columns was found to be effective one to improve the performance of crashworthiness.
Social