Difference between revisions of "Embedded Systems and autonomous UAVs"
From iis-projects
(→Available Projects) |
|||
Line 35: | Line 35: | ||
suppresserrors=true | suppresserrors=true | ||
category = Energy Efficient Autonomous UAVs | category = Energy Efficient Autonomous UAVs | ||
+ | </DynamicPageList> | ||
+ | <DynamicPageList> | ||
+ | category = Available | ||
+ | category = Digital | ||
+ | suppresserrors=true | ||
+ | category = SmartSensors | ||
+ | </DynamicPageList> | ||
+ | <DynamicPageList> | ||
+ | category = Available | ||
+ | category = Digital | ||
+ | suppresserrors=true | ||
+ | Category:Embedded Artificial Intelligence:Systems And Applications | ||
+ | </DynamicPageList> | ||
+ | <DynamicPageList> | ||
+ | category = Available | ||
+ | category = Digital | ||
+ | suppresserrors=true | ||
+ | category = EmbeddedAI | ||
</DynamicPageList> | </DynamicPageList> |
Revision as of 16:58, 10 November 2020
Short Description
Sensors and related technologies have enjoyed considerable success, as demonstrated by the increasing number of “smart” devices in use. From bracelets to glasses, from smartphones to smart shoes, from smart devices in home automation to professional healthcare systems, the commercial success of these smart objects is the result of vast improvements in electronics that has led to an increase in performance, while reducing the operational power as well as by the availability of ubiquitous wireless connectivity. The clear trend is toward billions of smart sensors, in the “Internet of Things” (IoT) vision. In fact, IoT creates formidable challenges for academic and industrial research. In particular, these billions of smart devices with sensors will produce a mind-boggling quantity of data that need to be processed to provide useful information. In fact, the data by themselves are not able to provide value unless they are not processed. Big-data mining techniques allow us to gain new insights by batch-processing and off-line analysis. However, this is not sufficient: in-situ real-time feature extraction, analysis, classification, and local decision-making are essential for a truly scalable and robust IoT infrastructure.
Machine learning technologies are extensively used with great success in many application domains to solve real-world problems in entertainment e-health, automatic surveillance, assisted living, and assistant driving among many others. More and more researchers are tackling classification and decision-making problems with the help of brain-inspired algorithms (i.e. neural network or convolutional neural network), featuring many stages of feature extractors and classifiers with lots of parameters that are optimized using the unprecedented wealth of training data that is currently available. These brain-inspired techniques are also known as multi-layer neural networks. In recent years, neural network has achieved results that exceed those achieved by humans on very challenging problems and datasets, and routinely surpass more mature ad hoc approaches. Neural network algorithms are extremely flexible and applicable to various data sources. They perform at best when information is spatially or temporally well localized, but still has to be seen in a more global context. However, neural networks approaches are still not suitable for wearable, ultra-miniaturized IoT devices, because, in their current embodiments, they require massive amounts of computational power.
Many of them are in collaboration with Swiss's companies that are interested in IoT and especially autonomous sensing systems. The following projects focus on processing data with machine learning on low power single-core microcontrollers (i.e. Arm-Cortex-M family) or MultiCore (i.e. PULP Processor designed in IIS)
Depending on the applicant's profile and project type, his tasks may involve some of the following:
- lab. testing/characterization of the existing prototype: verification of the prototype's characteristics w.r. design specification (simulations), measuring power-consumption, and assessing detection performance in lab. Conditions
- High-level software programming, machine learning, wireless communication
- Programming the circuit for specific applications, field testing, data acquisition
- Designing PCB with micro-controllers, wireless interfaces, energy harvesting and sensors and test on the field.
- Firmware implementation for low power and application.
- Analog/digital design using discrete components.
Prerequisites
(not all need to be met by the single candidate)
- Experience using the laboratory instrumentation - signal generators, oscilloscopes, DAQ cards, Matlab etc.
- analog electronics and signal conditioning with operational amplifiers: amplifiers, filters, integrators etc.
- knowledge of microcontroller programming and PC programming (C/C++, preferably microcontroller with Bluetooth Low Energy but it is not mandatory)
- basic knowledge on signal processing is a plus.
- plus is knowledge on printed circuit board (PCB) using Altium.
For a complete list of many cool projects please go to the following links
Available Projects
- Event-based navigation on autonomous nano-drones
- A Novel Execution Scheme for Ultra-tiny CNNs Aboard Nano-UAVs
- Improved Collision Avoidance for Nano-drones
- Deep Learning-based Global Local Planner for Autonomous Nano-drones
- Monocular Vision-based Object Following on Nano-size Robotic Blimp
- A Waypoint-based Navigation System for Nano-Size UAVs in GPS-denied Environments
- Covariant Feature Detector on Parallel Ultra Low Power Architecture
- GPT on the edge
- Exploratory Development of a Unified Foundational Model for Multi Biosignal Analysis
- Deep Learning Based Anomaly Detection in ECG Signals Using Foundation Models
- Pretraining Foundational Models for EEG Signal Analysis Using Open Source Large Scale Datasets
- EEG-based drowsiness detection
- In-ear EEG signal acquisition
- EEG earbud
- Advanced EEG glasses
- Skin Coupling Media Characterization For Fitness Tracker Applications (1 B/S)
- Integrating Ultrasound Technology into a Fitness Tracking Device (1M, 2 B/S)
- Testbed Design for Self-sustainable IoT Sensors
- Towards Flexible and Printable Wearables
- Modular Distributed Data Collection Platform
- Smart Goggles for Visual In-Action Feedback in Ski Jumping (1 M 1-2B/S)
- Wireless In Action Data Streaming in Ski Jumping (1 B/S)
- Object Detection and Tracking on the Edge
- Design of a Low Power Smart Sensing Multi-modal Vision Platform
- Design of a High-performance Hybrid PTZ for Multimodal Vision Systems
- BirdGuard
- ML based Quantitative Movement Analysis on a Portable IoT Camera (1-2S/B)
- Multisensory system for performance analysis in ski jumping (M/1-2S/B)
- Predict eye movement through brain activity
- Design of combined Ultrasound and PPG systems
- Improving datarate and efficiency of ultra low power wearable ultrasound
- Battery indifferent wearable Ultrasound
- Wearable Ultrasound for Artery monitoring
- Automatic unplugging detection for Ultrasound probes
- Short Range Radars For Biomedical Application
- Smart Patch For Heath Care And Rehabilitation
- Autonomus Drones With Novel Sensors And Ultra Wide Band
- BCI-controlled Drone
- Pressure and acoustic Smart Sensors Network for Wind Turbines Monitoring
- Design Of A Biomarker Assay Based On Responsive Magnetic Nanoparticles
- High-throughput Embedded System For Neurotechnology in collaboration with INI
- Neuromorphic Intelligence In An Embedded System in Collaboration with AiCTX
- Adversarial Attacks Against Deep Neural Networks In Wearable Cameras
- Wearable Smart Camera With Deep Learning Algorithms For Automatic Detecion
- Energy Efficient Smart Devices For Construction Building Maintenance Hilti Collaboration
- Improving Cold-Start in Batteryless And Energy Harvesting Systems
- Edge Computing for Long-Term Wearable Biomedical Systems
- Optogenetics And Game Theory Applied To Small Side Bird Using Smart Sensing
- Wireless Sensing With Long Range Comminication (LoRa)
- Indoor Smart Tracking of Hospital instrumentation
- A Wearable Wireless Kidney Function Monitoring System For BioMedical Applications
- Embedded Gesture Recognition Using Novel Mini Radar Sensors
- Contextual Intelligence on Resource-constraint Bluetooth LE IoT Devices
- An Industrial-grade Bluetooth LE Mesh Network Solution
- BLISS - Battery-Less Identification System for Security
- Zero Power Touch Sensor and Reciever For Body Communication
- Wake Up Radio For Energy Efficient Communication System and IC Design
- A Wireless Sensor Network for HPC monitoring
- Low Power One bit Microphone for Acoustic Imaging Using A Parallel Processor
- Low Power Geolocalization And Indoor Localization
- Autonomous Sensors For Underwater Monitoring In Smart Navy Systems
- Smart Wearable System For Vital Sign Monitoring Exploiting On Board and Cloud Machine Learning
- Radio Signal Direction Detection For Smart Glasses For Augmented Reality Applications
- A Wearable System To Control Phone And Electronic Device Without Hands
- Towards The Integration of E-skin into Prosthetic Devices
- Using Motion Sensors to Support Indoor Localization
- Low Power Neural Network For Multi Sensors Wearable Devices
- Kinetic Energy Harvesting For Autonomous Smart Watches
- Benchmarking RISC-V-based Accelerator Cards for Inference (multiple SA)
- Benchmarking a RISC-V-based Server on LLMs/Foundation Models (SA or MA)
- On-Device Learnable Embeddings for Acoustic Environments
- On-Device Federated Continual Learning on Nano-Drone Swarms
- Extending our FPU with Internal High-Precision Accumulation (M)
- Extreme-Edge Experience Replay for Keyword Spotting
- Low Precision Ara for ML
- Extending the HERO RISC-V HPC stack to support multiple devices on heterogeneous SoCs (M/1-3S)
- FPGA mapping of RPC DRAM
- GPT on the edge
- Exploratory Development of a Unified Foundational Model for Multi Biosignal Analysis
- Deep Learning Based Anomaly Detection in ECG Signals Using Foundation Models
- Pretraining Foundational Models for EEG Signal Analysis Using Open Source Large Scale Datasets
- Modeling FlooNoC in GVSoC (S/M)
- Advanced Data Movers for Modern Neural Networks
- Designing a Fault-Tolerant On-Chip Interconnect (1-2S/M)
- Hardware Exploration of Shared-Exponent MiniFloats (M)
- Scaleout Study on Interleaved Memory Transfers in Huge Manycore Systems with Multiple HBM Channels (M/1-3S)
- Creating an At-memory Low-overhead Bufferless Matrix Transposition Accelerator (1-3S/B)
- Advanced Physical Design: Reinforcement Learning for Macro Placement and Mix-Placer (B/1-2S)
- Vector-based Parallel Programming Optimization of Communication Algorithm (1-2S/B)
- EEG-based drowsiness detection
- In-ear EEG signal acquisition
- EEG earbud
- NeuroSoC RISC-V Component (M/1-2S)
- Scan Chain Fault Injection in a PULP SoC (1S)
- Routing 1000s of wires in Network-on-Chips (1-2S/M)
- Network-on-Chip for coherent and non-coherent traffic (M)
- Realtime Gaze Tracking on Siracusa
- Development Of An FPGA-Based Optoacoustic Image Reconstruction Platform for Clinical Applications
- Ultrasound measurement of microbubble stiffness for in situ detection of protease activity in clinical settings
- System Emulation for AR and VR devices
- Learning at the Edge with Hardware-Aware Algorithms
- Evaluating The Use of Snitch In The PsPIN RISC-V In-network Accelerator (M)
- Advanced EEG glasses
- Softmax for Transformers (M/1-2S)
- Skin Coupling Media Characterization For Fitness Tracker Applications (1 B/S)
- Integrating Ultrasound Technology into a Fitness Tracking Device (1M, 2 B/S)
- Testbed Design for Self-sustainable IoT Sensors
- Towards Flexible and Printable Wearables
- Modular Distributed Data Collection Platform
- Cycle-Accurate Event-Based Simulation of Snitch Core
- Smart Goggles for Visual In-Action Feedback in Ski Jumping (1 M 1-2B/S)
- Wireless In Action Data Streaming in Ski Jumping (1 B/S)
- A FPGA-based data streaming system that enables real-time monitoring of cell culture and neuroactivities
- Object Detection and Tracking on the Edge
- Design of a Low Power Smart Sensing Multi-modal Vision Platform
- Design of a High-performance Hybrid PTZ for Multimodal Vision Systems
- Energy Efficient AXI Interface to Serial Link Physical Layer
- Energy Efficient Serial Link
- Adaptively Controlled Polarization And Hysteresis Curve Tracing For Polymer Piezoelectrics (1 S/B)
- Development Of A Test Bed For Ultrasonic Transducer Characterization (1 S/B)
- BirdGuard
- ML based Quantitative Movement Analysis on a Portable IoT Camera (1-2S/B)
- Multisensory system for performance analysis in ski jumping (M/1-2S/B)
- Audio Visual Speech Separation and Recognition (1S/1M)
- Predict eye movement through brain activity
- Design of a Reconfigurable Vector Processor Cluster for Area Efficient Radar Processing (1M)
- Implementation of a Coherent Application-Class Multicore System (1-2S)
- Resource Partitioning of RPC DRAM
- Finalizing and Releasing Our Open-source AXI4 IPs (1-3S/B/2-3G)
- Towards a High-performance Open-source Verification Suite for AXI-based Systems (M/1-3S/B)
- All the flavours of FFT on MemPool (1-2S/B)
- Approximate Matrix Multiplication based Hardware Accelerator to achieve the next 10x in Energy Efficiency: Full System Intregration
- Ultrasound image data recycler
- Benchmarking a heterogeneous 217-core MPSoC on HPC applications (M/1-3S)
- Extended Verification for Ara
- Design of combined Ultrasound and PPG systems
- Accelerating Stencil Workloads on Snitch using ISSRs (1-2S/B)
- An Efficient Compiler Backend for Snitch (1S/B)
- PULP Freertos with LLVM
- Integration Of A Smart Vision System
- Towards Formal Verification of the iDMA Engine (1-3S/B)
- Event-based navigation on autonomous nano-drones
- Improving datarate and efficiency of ultra low power wearable ultrasound
- A Novel Execution Scheme for Ultra-tiny CNNs Aboard Nano-UAVs
- Battery indifferent wearable Ultrasound
- Wearable Ultrasound for Artery monitoring
- Machine Learning for extracting Muscle features from Ultrasound raw data
- Improved Collision Avoidance for Nano-drones
- Autonomous Mapping with Nano-Drones UWB and Novel Depth Sensors
- Autonomous Obstacle Avoidance with Nano-Drones and Novel Depth Sensors
- Deep Learning-based Global Local Planner for Autonomous Nano-drones
- Ultra-wideband Concurrent Ranging
- Enhancing our DMA Engine with Fault Tolerance
- Fast Accelerator Context Switch for PULP
- Visualization of Neural Architecture Search Spaces
- Self Aware Epilepsy Monitoring
- Serverless Benchmarks on RISC-V (M)
- Non-blocking Algorithms in Real-Time Operating Systems
- EEG artifact detection with machine learning
- Design of Time-Encoded Spiking Neural Networks (IBM-Zurich)
- EEG artifact detection for epilepsy monitoring
- Fast Simulation of Manycore Systems (1S)
- Training and Deploying Next-Generation Quantized Neural Networks on Microcontrollers
- Spiking Neural Network for Motor Function Decoding Based on Neural Dust
- Hardware/software codesign neural decoding algorithm for “neural dust”
- Automatic unplugging detection for Ultrasound probes
- Ibex: Tightly-Coupled Accelerators and ISA Extensions
- Huawei Research
- Securing Block Ciphers against SCA and SIFA
- RVfplib
- Exploring feature selection and classification algorithms for ultra-low-power closed-loop systems for epilepsy control
- Short Range Radars For Biomedical Application
- Smart Patch For Heath Care And Rehabilitation
- Autonomus Drones With Novel Sensors And Ultra Wide Band
- Evaluating memory access pattern specializations in OoO, server-grade cores (M)
- Machine Learning on Ultrasound Images
- IP-Based SoC Generation and Configuration (1-3S/B)
- Efficient Search Design for Hyperdimensional Computing
- PREM Runtime Scheduling Policies
- IBM Research
- RISC-V based Implementation of Secure Ranging According to IEEE 802.15.4z UWB
- BCI-controlled Drone
- Nanoelectrode array biosensors - programmable non-overlapping clocks generator project
- Accurate deep learning inference using computational memory
- Spiking Neural Network for Autonomous Navigation
- Event-Driven Convolutional Neural Network Modular Accelerator
- Pressure and acoustic Smart Sensors Network for Wind Turbines Monitoring
- Design Of A Biomarker Assay Based On Responsive Magnetic Nanoparticles
- High-throughput Embedded System For Neurotechnology in collaboration with INI
- Neuromorphic Intelligence In An Embedded System in Collaboration with AiCTX
- Adversarial Attacks Against Deep Neural Networks In Wearable Cameras
- Wearable Smart Camera With Deep Learning Algorithms For Automatic Detecion
- Visualizing Functional Microbubbles using Ultrasound Imaging
- Energy Efficient Smart Devices For Construction Building Maintenance Hilti Collaboration
- Extending the RISCV backend of LLVM to support PULP Extensions
- Compiler Profiling and Optimizing
- PREM Intervals and Loop Tiling
- Implementation of the RISC-V Bit Manipulation (RVB) extensions for our RISC-V core
- Implementation of the RISC-V Bit Manipulation (RVB) extensions for our RI5CY core
- Level Crossing ADC For a Many Channels Neural Recording Interface
- Scalable Heterogeneous L1 Memory Interconnect for Smart Accelerator Coupling in Ultra-Low Power Multicores
- Improving Cold-Start in Batteryless And Energy Harvesting Systems
- Cerebellum: Design of a Programmable Smart-Peripheral for the Ariane Core
- PREM on PULP
- Edge Computing for Long-Term Wearable Biomedical Systems
- AMZ Driverless Competition Embedded Systems Projects
- Optogenetics And Game Theory Applied To Small Side Bird Using Smart Sensing
- Wireless Sensing With Long Range Comminication (LoRa)
- Indoor Smart Tracking of Hospital instrumentation
- A Wearable Wireless Kidney Function Monitoring System For BioMedical Applications
- Physics is looking for PULP
- Embedded Gesture Recognition Using Novel Mini Radar Sensors
- Contextual Intelligence on Resource-constraint Bluetooth LE IoT Devices
- An Industrial-grade Bluetooth LE Mesh Network Solution
- BLISS - Battery-Less Identification System for Security
- Monocular Vision-based Object Following on Nano-size Robotic Blimp
- A Waypoint-based Navigation System for Nano-Size UAVs in GPS-denied Environments
- Zero Power Touch Sensor and Reciever For Body Communication
- Wake Up Radio For Energy Efficient Communication System and IC Design
- A Wireless Sensor Network for HPC monitoring
- High Speed FPGA Trigger Logic for Particle Physics Experiments
- Low Power One bit Microphone for Acoustic Imaging Using A Parallel Processor
- Low Power Geolocalization And Indoor Localization
- Real-Time Implementation of Quantum State Identification using an FPGA
- Neural Networks Framwork for Embedded Plattforms
- Hyper Meccano: Acceleration of Hyperdimensional Computing
- Autonomous Sensors For Underwater Monitoring In Smart Navy Systems
- Resilient Brain-Inspired Hyperdimensional Computing Architectures
- Variable Bit Precision Logic for Deep Learning and Artificial Intelligence
- Smart Wearable System For Vital Sign Monitoring Exploiting On Board and Cloud Machine Learning
- Tiny CNNs for Ultra-Efficient Object Detection on PULP
- Single-Bit-Synapse Spiking Neural System-on-Chip
- OpenRISC SoC for Sensor Applications
- Desing and Implementation Of Long Lasting Key Finder With Bleetooth Low Energy
- Radio Signal Direction Detection For Smart Glasses For Augmented Reality Applications
- PVT Dynamic Adaptation in PULPv3
- Passive and Self Sustaining Receivers For On and Intra Body Communication For Wearable Sensors Networks
- A Wearable System To Control Phone And Electronic Device Without Hands
- Towards The Integration of E-skin into Prosthetic Devices
- Ultra Low Power Conversion Circuit For Batteryless Applications
- Towards Self Sustainable UAVs
- Using Motion Sensors to Support Indoor Localization
- Low Power Neural Network For Multi Sensors Wearable Devices
- Bateryless Heart Rate Monitoring
- Birds Long Term Monitoring With Ultra Low Power Wireless Sensor Node
- Covariant Feature Detector on Parallel Ultra Low Power Architecture
- Ultra-Efficient Visual Classification on Movidius Myriad2
- Kinetic Energy Harvesting For Autonomous Smart Watches
- A Wearable System for long term monitoring of human physiological parameters with E skin sensors
- Autonomous Smart Watches: Toward an ultra low power microphone detector with events classification
- Autonomous Smart Watches: Hardware and Software Desing
- A Wireless Sensor Network for a Smart LED Lighting control
- Compressed Sensing vs JPEG
- Ultra-High-Efficiency Power Supply Management for Ultra-Low-Power Systems on Chip
- Real-Time Pedestrian Detection For Privacy Enhancement
- Thermal Control of Mobile Devices
- Android reliability governor
- Infrared Wake Up Radio
- Ambient RF Energy harvesting for Wireless Sensor Network
- Hardware Support for IDE in Multicore Environment
- Audio DAC Conversion Jitter Measurement System
- Hybrid Analog/Digital Leveling Loop for Very-Low-Distortion Oscillator
- Wiederverwendung (reuse) ganzer Funktionsblöcke beim VLSI-Entwurf
- Praxisgerechte Berechnung von Switching Noise in VLSI-Schaltungen
- Ultra Low Power Wake Up Radio for Wireless Sensor Network
- Variability Tolerant Ultra Low Power Cluster
- GPT on the edge
- Exploratory Development of a Unified Foundational Model for Multi Biosignal Analysis
- Deep Learning Based Anomaly Detection in ECG Signals Using Foundation Models
- Pretraining Foundational Models for EEG Signal Analysis Using Open Source Large Scale Datasets
- Development Of An FPGA-Based Optoacoustic Image Reconstruction Platform for Clinical Applications
- Ultrasound measurement of microbubble stiffness for in situ detection of protease activity in clinical settings
- Advanced EEG glasses
- Testbed Design for Self-sustainable IoT Sensors
- Towards Flexible and Printable Wearables
- Modular Distributed Data Collection Platform
- Object Detection and Tracking on the Edge
- Design of a Low Power Smart Sensing Multi-modal Vision Platform
- Design of a High-performance Hybrid PTZ for Multimodal Vision Systems
- Predict eye movement through brain activity
- Design of combined Ultrasound and PPG systems
- Wearable Ultrasound for Artery monitoring
- Machine Learning for extracting Muscle features from Ultrasound raw data
- Self Aware Epilepsy Monitoring
- EEG artifact detection with machine learning
- EEG artifact detection for epilepsy monitoring
- Automatic unplugging detection for Ultrasound probes
- Short Range Radars For Biomedical Application
- Smart Patch For Heath Care And Rehabilitation
- Autonomus Drones With Novel Sensors And Ultra Wide Band
- Machine Learning on Ultrasound Images
- BCI-controlled Drone
- Pressure and acoustic Smart Sensors Network for Wind Turbines Monitoring
- Design Of A Biomarker Assay Based On Responsive Magnetic Nanoparticles
- High-throughput Embedded System For Neurotechnology in collaboration with INI
- Neuromorphic Intelligence In An Embedded System in Collaboration with AiCTX
- Adversarial Attacks Against Deep Neural Networks In Wearable Cameras
- Wearable Smart Camera With Deep Learning Algorithms For Automatic Detecion
- Visualizing Functional Microbubbles using Ultrasound Imaging
- Energy Efficient Smart Devices For Construction Building Maintenance Hilti Collaboration
- Improving Cold-Start in Batteryless And Energy Harvesting Systems
- Edge Computing for Long-Term Wearable Biomedical Systems
- Optogenetics And Game Theory Applied To Small Side Bird Using Smart Sensing
- Wireless Sensing With Long Range Comminication (LoRa)
- Indoor Smart Tracking of Hospital instrumentation
- A Wearable Wireless Kidney Function Monitoring System For BioMedical Applications
- Embedded Gesture Recognition Using Novel Mini Radar Sensors
- Contextual Intelligence on Resource-constraint Bluetooth LE IoT Devices