Cutting-edge research at the intersection of hypervisors & operating systems, heterogeneous computing platforms, embedded & real-time systems, agile, autonomous robotics
We rethink when, how, and where computation happens in multi-core, heterogeneous, reconfigurable embedded systems: hypervisors, operating systems, on-chip FPGAs, and learning-based control.
- 77 papers since 2017
- 6 award-winning papers
- 22 code, hardware and data artifacts
- 12 lab members
Research areas
-
Partially Reconfigurable Platforms
FPGA-in-the-middle performance assessment and control on CPU+FPGA systems-on-chip.
17 papers -
Real-Time Virtualization
Hypervisor techniques for strong spatio-temporal isolation and workload-aware tuning.
6 papers -
Workload Profiling
Fine-grained knowledge of how applications interact with processors and memory.
9 papers -
Neural Network Control
Deployable, generalizable, and safe learning-based flight and robot control.
7 papers -
Memory & Shared-Resource Management
Regulating memory bandwidth, caches, and other shared resources so that timing stays predictable.
28 papers -
Unmanned Aircraft & Flight Testing
Instrumented unmanned aircraft, flight-test data sets, and long-endurance solar platforms.
10 papers
Recent publications
- Programmable Data Layouts via On-The-Fly Data Transformation
- Bottleneck-Aware Bandwidth Regulation for Heterogeneous Memory Subsystems
- Devil-in-FPGA: Coherent Trojans in Reconfigurable Heterogeneous Systems
- Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware
- Accelerating Lyapunov-Stable Neural Control using Fulfillment Priority Logic
- FRACTAL: Fast Reverse Address translation over Coherence for Tracing And Logging
Honors
- Best Demonstration AwardTII GenZero Workshop, 2024Shahin Roozkhosh, Bassel El Mabsout, Patrick Carpanedo, Denis HoornaertChallenge 6.
- Second place, F1Tenth autonomous racingF1Tenth competition, 2024Bassel El Mabsout, Patrick Carpanedo, Koneshka Bandyopadhyay, Hyunjin Jung
- Early Career Researcher AwardACM SIGBED, 2024Given each year to one junior researcher in embedded, real-time and cyber-physical systems.
- BU Computer Science Research Excellence AwardBoston University, 2024Shahin Roozkhosh
- Best Demonstration AwardVLDB (Very Large Data Bases), 2023For the demo “On-the-fly Data Transformation in Action”.
- Nominated for Supervisor of the YearBoston University, 2023Nominated by five Ph.D. students.
- Gitner Family Award for Innovation in Teaching with TechnologyBoston University, 2023
- NSF CAREER AwardNational Science Foundation, 2023
- Best Reviewer AwardIEEE RTSS, 2022
- IEEE Senior MemberIEEE, 2022
Paper awards
- Best Paper Award RTSS 2024Coherence-Aided Memory Bandwidth Regulation
- Outstanding Paper Award, Best Presentation Award ECRTS 2023Low-overhead Online Assessment of Timely Progress as a System Commodity
- Outstanding Paper Award ECRTS 2023Memory Latency Distribution-Driven Regulation for Temporal Isolation in MPSoCs
- Best Student Paper Award RTSS 2020E-WarP: a System-wide Framework for Memory Bandwidth Profiling and Management
- Best Paper Award RTAS 2020The Potential of Programmable Logic in the Middle: Cache Bleaching
- Outstanding Paper Award ECRTS 2019Designing Mixed Criticality Applications on Modern Heterogeneous MPSoC Platforms
About the lab
The mission of the Cyber-Physical Systems Lab (CPSLab) at Boston University is to rethink and re-design when, how, and where computation happens in modern multi-core, heterogeneous, dynamically re-reconfigurable embedded systems. The research propelled in the lab aims at harvesting the unprecedented potential of bleeding-edge embedded technology to deliver solid foundations for the development of next-generation cyber-physical systems. These include self-driving cars, green-energy UAVs, machine-learning-enabled robotics controllers, IoT and edge-cloud devices, to name a few.
The challenges tackled at the lab span from hypervisor technologies to enforce strong performance isolation, to OS-level solutions to conduct accurate workload profiling and management; from leveraging the power of machine learning in bare-metal micro-controller firmware, to elevating performance self-awareness via on-chip reconfigurable hardware.
The lab is affiliated with the Department of Computer Science at Boston University. It is led by PI Renato Mancuso, Ph.D. and includes multiple Ph.D., M.S. students, and volunteers at different stages of their academic and professional careers.
Affiliated institutions
-
Non-profitNeobotics
Standardizing and democratizing autonomous vehicle education through accessible racing platforms and open curriculum.
-
StartupMinerva Systems
Embedded system software and development tools for future autonomous systems.
-
CompanyAl Volo
Plug-and-play flight data acquisition systems for unmanned aircraft.