- 31
- 60 020
D-ITET Center for Project-Based Learning
Switzerland
Приєднався 18 тра 2020
The main aim of the D-ITET Center for Project-Based Learning (PBL) is to build its activities at the department level with a centralized structure. The center will primarily focus on creating, promoting and providing education and courses with projects and hands-on practice for students.
Learning-Based On-Track System Identification for Scaled Autonomous Racing in Under a Minute
Traditional tire modeling for autonomous racing requires extensive testing in controlled conditions - but what if we could learn tire behavior directly on the racetrack? We present a novel system identification algorithm that combines neural networks with traditional methods to learn accurate tire models during actual racing. Through iterative refinement and virtually generated data, our approach achieves 3.3x lower error rates than standard nonlinear least squares methods.
The key breakthrough: we can now learn a complete tire model with just 30 seconds of driving data and 3 seconds of training time, matching the accuracy of traditional steady-state methods - all while operating in dynamic racing conditions rather than requiring specialized testing facilities.
github: github.com/ForzaETH/On-Track-SysID
preprint: arxiv.org/pdf/2411.17508v1
The key breakthrough: we can now learn a complete tire model with just 30 seconds of driving data and 3 seconds of training time, matching the accuracy of traditional steady-state methods - all while operating in dynamic racing conditions rather than requiring specialized testing facilities.
github: github.com/ForzaETH/On-Track-SysID
preprint: arxiv.org/pdf/2411.17508v1
Переглядів: 123
Відео
Predictive Spliner: Data-Driven Overtaking in Autonomous Racing Using Opponent Trajectory Prediction
Переглядів 6702 місяці тому
Head-to-head autonomous racing presents significant challenges in real-time opponent management. We present Predictive Spliner, a data-driven overtaking planner utilizing Gaussian Process regression to model opponent behavior and compute optimal overtaking trajectories. Experimental validation on 1:10 scale autonomous vehicles, using LiDAR-based opponent detection, demonstrates overtaking capab...
Obstacle Avoidance with Ultrasonic Sensors on Nano-UAVs
Переглядів 2203 місяці тому
Credits to Laurent Schroeder
ForzaETH Race Stack - Hardware Tutorial
Переглядів 9463 місяці тому
This video is the third part in a three-part miniseries introducing the ForzaETH Race Stack, and describes how to use it to operate a physical F1TENTH car for time-trial and head-to-head races Note : the mentioned alias `sauce`, re-sources the local ROS 1 workspace, and can be added by adding the following line to your `.bashrc` file, in case the workspace path is the same and you are using bas...
ForzaETH Race Stack - Installation Tutorial
Переглядів 3163 місяці тому
This video is the first part in a three-part miniseries introducing the ForzaETH Race Stack, and describes how to install the system both in its ROS 1 and ROS 2 version, using docker as a containerization environment Timeline: 00:00 Intro 01:10 ROS 1 Installation 11:23 ROS 2 Installation 22:55 Outro Video Credits: Niklas Bastuck, Tobias Kränzlin, Michael Lötscher, Luca Tognoni GitHub Repository...
ForzaETH Race Stack - Simulation Tutorial
Переглядів 5943 місяці тому
This video is the second part in a three-part miniseries introducing the ForzaETH Race Stack, and describes how to setup, dynamically reconfigure, and use the simulator, for time trials and head-to-head racing Timeline: 00:00 Intro 01:00 The Simulator 01:59 ROS 1 - Launching the Sim 03:33 ROS 1 - Running Time-Trials 04:12 ROS 1 - Running Head-to-Head 05:03 ROS 1 - RQT & Dynamic Reconfigure 05:5...
CR3DT: Camera-RADAR Fusion for 3D Detection and Tracking
Переглядів 6204 місяці тому
This paper was accepted at IROS 2024. To enable self-driving vehicles accurate detection and tracking of surrounding objects is essential. While Light Detection and Ranging (LiDAR) sensors have set the benchmark for high-performance systems, the appeal of camera-only solutions lies in their cost-effectiveness. Notably, despite the prevalent use of Radio Detection and Ranging (RADAR) sensors in ...
Relative Infrastructure-less Localization Algorithm for Decentralized and Autonomous Swarm Formation
Переглядів 1338 місяців тому
GitHub repository: github.com/ETH-PBL/swarm-relative-localization Paper: ieeexplore.ieee.org/document/10342168
Fully Onboard SLAM for Distributed Mapping with a Swarm of Nano-Drones
Переглядів 98510 місяців тому
The use of Unmanned Aerial Vehicles (UAVs) is rapidly increasing in applications ranging from surveillance and first-aid missions to industrial automation involving cooperation with other machines or humans. To maximize area coverage and reduce mission latency, swarms of collaborating drones have become a significant research direction. However, this approach requires open challenges in positio...
Stargate: Multimodal Sensor Fusion for Autonomous Navigation on Miniaturized UAVs
Переглядів 48310 місяців тому
Autonomously navigating robots need to perceive and interpret their surroundings. Currently, cameras are among the most used sensors due to their high resolution and frame rates at relatively low energy consumption and cost. In recent years, cutting-edge sensors, such as miniaturized depth cameras, have demonstrated strong potential, specifically for nano-size UAVs, where low power consumption,...
NanoSLAM: Enabling Fully Onboard SLAM for Tiny Robots
Переглядів 8 тис.Рік тому
Perceiving and mapping the surroundings are essential for enabling autonomous navigation in any robotic platform. The algorithm class that enables accurate mapping while correcting the odometry errors present in most robotics systems is Simultaneous Localization and Mapping (SLAM). Today, fully onboard mapping is only achievable on robotic platforms that can host high-wattage processors, mainly...
Scientifica preview: nano-UAV autonomous navigation
Переглядів 536Рік тому
Credits to: Alberto Schiaffino, Tommaso Polonelli, Vlad Niculescu, Hanna Müller, Konstantin Kalenberg
F1TENTH autonomous racing: onboard view
Переглядів 1,8 тис.Рік тому
This video introduces the PBL flagship project on autonomous racing. F1TENTH is an open source community driven autonomous racing platform, organizing semi-annual races hosted at robotics conferences such as IROS and ICRA. The ETH team is constantly on the lookout for motivated and talented students to join the team. More information on F1TENTH: f1tenth.org/ For ETH students wanting to join: et...
Model- and Acceleration-based Pursuit Controller for High-Performance Autonomous Racing
Переглядів 3,3 тис.Рік тому
Model- and Acceleration-based Pursuit Controller for High-Performance Autonomous Racing
PBL Flagship Project: SmartPatch for Biomedical Applications
Переглядів 3102 роки тому
PBL Flagship Project: SmartPatch for Biomedical Applications
Smart Agricolture: eco-firendly raven detection system
Переглядів 1562 роки тому
Smart Agricolture: eco-firendly raven detection system
Enabling Obstacle Avoidance for Nano-UAVs with a multi-zone depth sensor and a model-free policy
Переглядів 1,2 тис.2 роки тому
Enabling Obstacle Avoidance for Nano-UAVs with a multi-zone depth sensor and a model-free policy
IPSN2022 Demo Abstract: Towards Reliable Obstacle Avoidance for Nano-UAVs
Переглядів 1,1 тис.2 роки тому
IPSN2022 Demo Abstract: Towards Reliable Obstacle Avoidance for Nano-UAVs
LightTrackingRobot - P&S Microcontrollers for IoT
Переглядів 2022 роки тому
LightTrackingRobot - P&S Microcontrollers for IoT
Batteryless Smart Camera MAX78000 Challenge
Переглядів 7393 роки тому
Batteryless Smart Camera MAX78000 Challenge
PBL Wireless Smart Bracelet for EMG onboard data processing
Переглядів 1523 роки тому
PBL Wireless Smart Bracelet for EMG onboard data processing
A Battery-Free Long-Range Wireless Smart Camera for Face Recognition
Переглядів 1644 роки тому
A Battery-Free Long-Range Wireless Smart Camera for Face Recognition
Cisco Global Problem Solver Challenge 2020
Переглядів 1274 роки тому
Cisco Global Problem Solver Challenge 2020
Sen türkmüsün
Amazing rover ❤🎉😊
Is it working on jetson xavier? there's an issue when i do docker build base_arm.
Yeah this should work with xavier. Can you open an issue on the github repo and detail the issue?
This is vey insightful thankyou
THROUGH GOES HAMILTON!
Amazing rovers car, excellent work friend!❤🎉😊
Can you please share circuit connections and Source code
pls circuit diagram
greeat job
woow
Wow amazing!!
Veeery nice
Very nice, will you port it to Rust?
We welcome you to contribute to this open-source project!
Nice!
Is the loop closure scan and reference scan required because of a lack of precision with the odometery? Or is this typical of all robotics? I know there are plenty of issues for real world vs simulated location/trajectory in quadrupeds. If a more sensitive TOF sensor were used, maybe a rgb-d camera, would you still lack precision? Or could you include redundant positioning with a secondary IMU?
Amazing 🎉 Excellent work!😃👍
I would like to ask a question about F1tenth. Can you give me your email address?
The overtake at the end is crazy!!!
the RAL paper?
Hey compliments on the research work. Just one question as you are using plain cardboard boxes and apparently there are not a lot of things in the maze, how is the drone being able to localize?
Very interesting video, awesome work!🤩👍
Very nice :) to take care of visual odometry drift with graph based approach. I have a doubt, can the onboard IMU be used to take care of this drift ? The main reason being for this graph to make a SLAM, it needs a closed graph path. Can IMU make a difference with a kalman filter maybe ?
Can you made diy video how to make this emg bracelet
Great job! Absolute stunning work! 👍
we need to use in cart can you help us to develop it !!
Impressive! Keep up the good work
wonderful work!
Hi, how did you power up Intel NUC using Li-Po battery?
yes
using lipo 4s 5000Mah and step-up
will it shut down when the motors run?
@@phantommedia9964 yes as seen in the video
Great Project.