![Apex AI](/img/default-banner.jpg)
- Видео 46
- Просмотров 290 184
Apex AI
Добавлен 13 ноя 2018
Apex.AI - Redefining mobility software development
Apex.AI - Redefining mobility software development
Просмотров: 393
Видео
driveblocks and Apex.AI join forces to deliver the Mapless Autonomy Platform with Apex.Grace!
Просмотров 331Год назад
Fusing driveblocks' perception solution for mapless autonomous driving with Apex.Grace's low-latency and #real-time capabilities of the Apex.AI base software, driveblocks is offering the Mapless Autonomy Platform. #autonomousvehicles #autonomoustrucking #SDV #SoftwareDefinedVehicle #ELIV2023 #ApexAI #FunctionalSafety #EmbeddedSoftware
Apex.AI at the Detroit Auto Show's autoMOBILI-D
Просмотров 555Год назад
Apex.AI at the Detroit Auto Show's autoMOBILI-D
The future of mobility - Driven by software
Просмотров 384Год назад
video credit: auto motor und sport Kongress 2023 Reflecting on the auto motor und sport Kongress-an inspiring event! Our CEO, Jan Becker, engaged in a thought-provoking panel alongside Sascha Meyer from MOIA.
Apex.AI - 50 German Leaders
Просмотров 1,3 тыс.Год назад
Apex.AI is a Palo Alto, Berlin, Munich, Stuttgart, and Gothenburg-based company that develops secure, certified, developer-friendly, and scalable software for mobility systems. Mining the insight of business leaders and senior decision-makers, the 50 German Leaders series explores the innovation driving global business expansion.
driveblocks | Apex.AI
Просмотров 1,4 тыс.2 года назад
While Apex.OS is a fork from ROS2; it has been optimized to meet the criteria of production-grade safety critical software and is, therefore, a perfect match for the task. driveblocks leverages the modularity of the node structure within the ROS universe to combine the perception stack in two configurations comparing varying parallelization levels in both frameworks.
Apex.AI - Enabling software-defined vehicles.
Просмотров 1,2 тыс.2 года назад
What if cars could be as easy to program as smartphones are today?
Apex.AI - The vehicle OS company.
Просмотров 2,2 тыс.2 года назад
Apex.AI is developing breakthrough software for mobility, smart-machines and IoT. Learn more about Apex.OS, the first and only safety-certified end-to-end operating system, and Apex.Middleware. Like Apple’s iOS software development kit, which enables practically anyone to create an iPhone app, Apex.OS makes programming a vehicle almost as easy as programming a phone. Apex.AI is backed by Toyota...
Lock free ROS 2 executor: A ring buffer to rule them all - Pablo Ghiglino
Просмотров 9503 года назад
get the slides: www.apex.ai/roscon-21
Executor with wait set and polling subscription - Michael Pöhnl
Просмотров 1,2 тыс.3 года назад
get the slides: www.apex.ai/roscon-21
Callback groups executor - Ralph Lange
Просмотров 8393 года назад
get the slides: www.apex.ai/roscon-21
Tune the system for real time - Andrei
Просмотров 6523 года назад
Tune the system for real time - Andrei
Tracing the reference system - Christophe Bédard
Просмотров 3893 года назад
Tracing the reference system - Christophe Bédard
Introduction to the reference system - Evan Flynn
Просмотров 9113 года назад
Introduction to the reference system - Evan Flynn
Current status of executor in ROS 2 Galactic - William Woodall
Просмотров 2 тыс.3 года назад
Current status of executor in ROS 2 Galactic - William Woodall
Back to the Future: The History and Future of Autonomous Vehicles
Просмотров 1,1 тыс.4 года назад
Back to the Future: The History and Future of Autonomous Vehicles
Autoware Course Lecture 14: HD Maps
Просмотров 18 тыс.4 года назад
Autoware Course Lecture 14: HD Maps
Autoware Course Lecture 13: Data Storage and Analytics
Просмотров 3,8 тыс.4 года назад
Autoware Course Lecture 13: Data Storage and Analytics
Machine Learning For The Safety Validation Of Autonomous Vehicles
Просмотров 2,1 тыс.4 года назад
Machine Learning For The Safety Validation Of Autonomous Vehicles
Autoware Course Lecture 12: Motion Control
Просмотров 13 тыс.4 года назад
Autoware Course Lecture 12: Motion Control
im getting a weird result: velodyne not found or something
as a student, how to learn more about apex product?
The Audio isnt working
Just want to clarify one thing that 3:45 China is not "Republic of China". Haha
So cool! Very effective improvement. Also appreciate being able to put a face to the name I have been seeing for the last two years as I learn about the Create3.
which coding language is used in automotive software industry
Can you share some output data of reference-system?
The SVL simulator does not work anymore. what alternatives do i pursue? please help
Since the SVL simulator has sunsetted, is there any alternate way we can still pursue the objectives of this lecture series?. If yes, using which other softwares/simulators?
Very interesting tutorial. Thank you
Coming back here after having watched the 14 videos of the course. It is amazing that such awesome content is uploaded freely on RUclips. Thank you very much.
does it worth it still? I dont want to waste my time..
ROS2 based system is still far from series production
I have a Continental Radar 408-21. I wanted to get the radar data in ROS2. but maximam Distance Longtidunal is approx 12 (m), not more than that. Could you please tell me, why am I not getting longtidual distance more than 12 meters?
This course is outdated and no more matching to the contenent.
are you sure?
Hi, I am getting below error while executing ./scripts/enter-container command. Could you please hep me out. Error response from daemon: Container dbb17091900b6030d372db7cab2848af562ffd3b40fb97ec03a8fa1e464bc546 is restarting, wait until the container is running
Is there an Autoware module for the lane recognition? Or is it necessary to use the NVIDIA DRIVE module?
Great
Hi, For yielding the car stops at the roundabout even when there is no car in it. Can you elaborate how is the yielding logic implemented? I see that there are certain areas marked on the map on which the ego vehicle pays attention.
Everything is cool but is it me that can't make sense or you guys keep saying your machine should have ubuntu 18.04 but you write the ADE image for ROS2 Foxy which runs on ubuntu 20???
Are there any additional method to avoid dust, snow and rain? I think vertical ray is really reasonable method for object detection, but really sensitive to noise.
Hi Team Thank you very much. This was very usefull course. Please provide same complete video's course for autoware.ai.
As iam building in both .ai and .auto also
This is great! for a long time, we were missing proper content on youtube related to the automotive industry and specifically the trends, new technologies, and development methods.
Hi, is it possible to run autoware without giving a prior 3D map ??
very impressive lecture. but i have a problem that the image is foxy-based, how could i get a image base on dashing?
Lane Detection demo is very difficult to understand for the beginners to run it following the video. Specially how to clone the codes and where to put them and how to source them and run them properly very hard to understand and follow from the video. be able to run the code is important for the beginner otherwise will be frustrated! even in the lecture slides no instructions for step by step running the demo
I am at very initial stage. it seems initial steps are skipped very fast and hard to understand how to start step by step. After cloning I did not see any directory called Camera-Hands-On-video-WS but on the video it seems it was in two terminal window
Naiceeeee
the car is stuck after to try play the replay, its looks like with the brakes on
Had problems installing the ade, the gitlab site has been removed. Anyone else had this problem?
Everything was okay, except the Lidar!
Thanks for your videos, Can I put Carla simulator such as sub module?
Hello, thanks for the course, it will be very useful for me! I would like to know if Ubuntu 18.04 can be switched for a more recent release such as 20.04 LTS or 21.04? Are there any reported issues regarding this switch?
any update for it?
This is the problem with open source and universities, they are 5 years behind the technology...
This was a waste of time.. The DDS guy with consolidated distributed robot architectures with FIR filters was clueless.
What would you have liked to see instead? For folks that are new to DDS and distributed robotic systems, this is a valuable resource. It seems you're just more familiar than most!
@@LyleAtApexAI I was actually hoping to figure out why DDS is useful in autonomous driving.
@@blanamaxima in absolute short, DDS is valuable for connecting the distributed compute systems that are becoming (IMO are) omnipresent in the automotive industry. DDS is also great at instilling standardized application interfaces through the use of IDL for data structures.Lastly, DDS is very powerful in a developer's hands, particularly because of the quality of service settings (QOS) which enable developers to programmatically change the behavior of the system (like if the network is saturated, what data must be sent vs what can be dropped). All this said, the middleware needs for automotive go far beyond any single protocol; many protocols must be supported to facilitate the many types of communication that are required. Beyond this, I'd encourage you to reach out to us at Apex.AI, or the Autoware.Auto / ROS 2 community through Discourse, if you want to share and learn more.
@@LyleAtApexAI I agree it is useful in automotive but I the course here is about autonomous driving and I see no point for it in autonomus driving. There is no point for Ethernet as we have sensors with bandwidth way beyond that. From cost perspectiv Ethernet is worse than Lvds so again why DDS for autonomous driving?
great video, but i dont understand why the walker is not detected, can you explain it?
Might be related to parameters-calibration or code etc. But, In general, I think reflection from the metal surfaces are much stronger than the human body or stones or tree etc.
I did food delivery in your headquarter :) came here for check
Next time stay for a coffee and we can show you the car! We'll have to see about the check ;)
Amazing lectures!
Simple and clean installation guide! I was using Ubuntu 20.04 LTS with GTX3060. The installation manual didn't work after clean installation of Ubuntu. So, beware of the prerequisite which is Ubuntu 18.04.
Do you mean that it is recommended to opt for Ubuntu 18.04 instead of Ubuntu 20.04 LTS?
Great engineering
is the document for safety software named "Development of A complex and safety-critical software in operational domains" shareable? @ApexAI
which 5 countries offer Autoware courses? Can you please mention ?
start !
Can this applied to real time?
Yes
Hi, I am not able to see the /opt/ros/dashing/ instead I could see the foxy. Inside docker the below commands not working ade$ ros2 run demo_nodes_cpp talker ade$ sudo apt update ade$ sudo apt install ros-dashing-turtlesim ade$ sudo apt install ros-dashing-rqt-* ade$ sudo apt install byobu any helps appreciated
🤯wow
Nice Video! One question: is there a mpc controller using dynamic model in autoware?
A basic kinematic bicycle model is used in the Autoware.Auto MPC controller, here's the design document --> autowarefoundation.gitlab.io/autoware.auto/AutowareAuto/mpc-controller-design.html. This is what was used in the Autonomous Valet Parking demo.
Thank you so much for sharing. Awesome content and presentation!It greatly broadens my views for motion planning.
Thank you for sharing us an amazing courses! Can I ask some question about the Autoware.AUTO NDT localization architecture? I am curious that in order to perform an initial guess/pose for NDT scan matching, why do the the ekf_node mentioned at 55:51 was only set or dedicated to odometry state estimator (e.g. wheel encoders, visual odometry, accelerometer, gyroscope) instead of having global state estimator (e.g. GPS)? or just showing that in case of there is no any GPS measurement being observed? Could you please briefly explain about this initialization? Thank you.
Hi Surachet, it was a design decision to not require GPS. See this section of the design docs (autowarefoundation.gitlab.io/autoware.auto/AutowareAuto/localization-design.html#autotoc_md470). It is of course possible (and popular) to use GPS for the initial pose; again, this was just not part of the initial ODD for Autoware.Auto. It's likely future ODDs for Autoware.Auto will include this feature though.
@@LyleAtApexAI Got it!, thank you so much
Super nice!!! The visualization was in rviz2 AutowareAi or AutowareAuto or another tool? The white lane is global path possible paths, or represents the car turning radius🤔? I noted the green line is followed but not the white line options, why?
Hey Marcus, this was from 2018 and at the time rviz (from ROS 1) was used. Through 2019 and to now the community and Apex.AI is able to use all ROS 2-based tooling (e.g. rviz2, rosbag2, rqt, ros2cli, etc.). I'm not sure what you mean by the white lane -- the gray lanes show the pathways / road that exist in the HD map along with the semantic information like lane and light positions. The lightly transparent green line is the desired route. You'll notice the waypoints are also visualized and always are placed dead-center of the desired route. The waypoints serve as an input to the planner module. The white line that sweeps across the screen (and originates from the host vehicle) is showing the output of the planning module which is used by the controller. The planner uses the waypoints, a look-ahead distance, and other inputs to determine and output a trajectory. The trajectory is taken by the controller to determine control commands that will then drive the vehicle along the path (while avoiding obstacles detected by the perception subsystems). There is great material in the Autoware.Auto project (autowarefoundation.gitlab.io/autoware.auto/AutowareAuto/avpdemo.html) that provides details about the architectures used for specific ODDs in autonomous driving.
@@LyleAtApexAI amazing answer Lyle thanks a lot. I have already done all AutowareAuto course it is super good framework, you are right! However to complete my master research this software does not address my needs: Switch local planners or global planners and evaluate them doing a Benchmark of path length, path smootheness, trajectory execution time, etc as the MoveIt framework provides in ROS1 for antrophomorphic robots. I am starting using now AutowareAI and I would like to know from you that already used it. If this framework offers this possibility of exchange planners through the runtime manager interface. Actually my doubt is a little more deep to post here. Please if you can help me in this regard could you answer this question in git: gitlab.com/ApexAI/autowareclass2020/-/issues/89 I am kind of frustrated because I have spent a lot of months with Navigation Stack in ROS 1 to create a simulation, but there is just TEB local planner that works with cars...also spent too much time with AutowareAuto, and I expected AutowareAuto would offer the runtime-manager interface, but they did not maybe because it is used for commercial purposes, who knows. And I ask myself if AutowareAI will offer this Benchmark plots (maybe through Rosbag) or at least to switch at least 3 different local planners or global planners. Would you know to answer this question my colleague? Thanks very much in advance
@@MarcusVinicius-lq3fe for sure, I'll do what I can to point you in the right direction in the GitLab issue.
@@LyleAtApexAI Hi thanks very much I am doing my best! Actually I have installed Autoware.AI on last days and I am testing with SVL simulator! It is amazing. The only issue that I have is when creating the custom scenario that I need with Visual Scene Editor or Python API. And Aftewards integrating them with the Autopilot of AutowareAI- ROS bridge.... The SVL simulator open and closes after seconds (says cluster is busy, bridge was disconnected)...also it seems that ROS is not subscribing to the right topics! well is there a chanel where we could "exchange pictures" as we say here in Brazil... I mean I have a lot of videos and attempts that are almost working...the SVL staff also is trying to figure out the issues. However they just have a robust system for VSE/PythonAPI integration Apollo 5. I am thinking if I should learn Apollo5 is it ROS based too? Well my deadline to deliver master is too short, sorry to trigger Autoware staff everytime, but I really need a God hands! hehe Thanks Lyle!!!
Autoware.auto has already a number of features, I do not understand why only .ai is covered but not .auto at all in this lecture.