Classify Object Behavior to Enhance the Safety of Autonomous Vehicles (Project 221)

[robertogl]

Contribute to the discussion by asking and/or answering questions, commenting, or sharing your ideas for solutions to project 221

[DHEEPAK29]

Hello, I'm interested collaborating this project.
Dheepak, IN

[DHEEPAK29]

Hi,
Got a good understanding of the project on the Objective, working, and tool sets.

Design for various scenarios to train the model is done and sensor data for the designed scenarios are collected accordingly using the drivingScenarioDesigner tool.
Solution Repository --> https://github.com/DHEEPAK29/Classify-Object-Behavior-to-Enhance-the-Safety-of-Autonomous-Vehicles.git

I have been stuck at this point of the project work. As I'm clueless about how to proceed further and I have some more questions to discuss with you in detail, If you have some time Could you please help me?

[DHEEPAK29]

Yes, For sample I've done for few instances using drivingScenarioDesigner tool.

[DHEEPAK29]

Hi @robertogl , Could you please help me on proceeding with further objective

[robertogl]

Hi @DHEEPAK29

Happy new year! Sorry for the late response, but I am finally back.

I am not sure how many instances you have created but you would need enough to be able to train a NN model.
Then you should use data from the simulated sensors to understand whether the behavior of external objects, like pedestrian or other vehicles, is safe or not so that you can label the data (for example from a simulated camera images, or lidar, or both) and start the training. To characterize the objects' behavior as safe or not safe you will need to have info about their motion, so output from a tracking algorithm might be needed.

After you have trained the model you will have to test it in a new test scenario and and check its performances.

I hope this gives you some inputs to move your project forward. Please let me know if you need anything else.

[DHEEPAK29]

Hi @robertogl, Sorry, I was in a rush for few weeks. As you told I've created few scenarios, further I'll elaborate multiple scenario. For labelling the Features, We have 2 either safe or unsafe. So, If I have many obstacles in a single scenario for example a pedestrians or a barrier. Both of them are different entity, For Pedestrian, The vehicle should stop till the person passes and for barrier the vehicle can take a turn if optimum space is available in the road, Thus, Two actions are entirely different. So, Is it sufficient to classify the instances with only 2 labels i.e., Safe & Unsafe. Can you reflect your idea on this.

[robertogl]

Hi @DHEEPAK29,

That is a very good point. I think using just the 2 labels, 'Safe' and 'Unsafe' it is a great start and they are good enough to decide whether continue via the planned trajectory/task or change maneuver, respectively. In case of Unsafe state, there might be different reactions as you correctly pointed out, but that can be decided based on the obstacle's type and/or motion. However, I think that is normally taken care of by a different layer, which includes object detection. Does it make sense?

[VoidXia]

Hi @robertogl , I am also trying to work on this project. I was curious to know if we need to manually create the dataset or if there is an existing one we can use. While I understand the idea of creating various driving scenarios and labeling them as safe or unsafe, I am concerned that manually creating a sufficient amount of data for the neural network model's training may prove to be challenging. Additionally, you had mentioned the need for a tracking algorithm. I was wondering if you had any suggestions for such an algorithm. It seems to me that the result of the project "Traffic Data Analysis for Modeling and Prediction of Traffic Scenarios" might be of relevance here. I would love to hear your thoughts. Thanks!

[robertogl]

Hi @VoidXia,

I totally understand your concern. I am not aware of any dataset out there but that does not mean that some may not exist already.
Regarding creating a new one from a simulation environment, we were thinking that that process could be, at least partially, automated, by changing the environment by adding or removing objects, changing motion, behavior, etc.

We have many tracking algorithms in our Sensor Fusion and Tracking Toolbox. A simple Kalman Filter could work for objects with linear motion models but we have more advanced multi-object trackers and many examples for autonomous systems.
Perhaps you can start from one of these examples and adapt it to your application.

[Eladki]

Yeah, I agree Roberto. You can track using the Sensor Fusion and Tracking Toolbox and the links that he provided are where I would start.

[K-Yogesh-Mishra]

Hello @robertogl I have submitted the solution to the problem, when should i expect a response from MATLAB side.

[robertogl]

Got it, thanks. You can paste all that information in the README file. If you are familiar with markdown you can have a similar nice formatting. Also, no need to zip the files for GitHub.

[robertogl]

Oh I forgot...There is no license in your repository. Would you be willing to release your code under an open source license (2-clause BSD or MIT)?

[K-Yogesh-Mishra]

Yes i am ok to release it as open source license with MIT and i will upload all the info in readme file. Do you need any other help for evaluating my solution.

[K-Yogesh-Mishra]

@robertogl Is my github repo ok for now?

[robertogl]

I see that you currently have the 'Apache-2.0' license, can you change it to 2-clause BSD or MIT?
Also, it would be great if you could also add pics and videos in the README file.
Thanks!

[K-Yogesh-Mishra]

Fixed! I have also uploaded the link which contains video and image explanation please look into it.

…

On Mon, Aug 12, 2024 at 9:17 PM robertogl ***@***.***> wrote: I see that you currently have the 'Apache-2.0' license, can you change it to 2-clause BSD or MIT? Also, it would be great if you could also add pics and videos in the README file. Thanks! — Reply to this email directly, view it on GitHub <#53 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BCBJR7N7QGZAVYWN6YLPG6LZRDKJLAVCNFSM6AAAAABLSQD45OVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTAMZRGYZDENA> . You are receiving this because you commented.Message ID: <mathworks/MATLAB-Simulink-Challenge-Project-Hub/repo-discussions/53/comments/10316224 @github.com>

[JakubSchwenkbeck]

Hey :)
Im working on this project since roughly a month and a half and wanted to ask if anyone had some ideas for extension/improvement : Repository . Im kind of stuck by creating data/own labels, I thought about generating both of them with a program but haven't had the time to do so yet.
Happy to hear some feedback!

[JakubSchwenkbeck]

Hey!
I now submitted my project, but I still would like to have conversations about this topic, feel free to start any kind of discussion :)

[Byleenroy300903]

Hello everyone! This is Byleen from Loyola ICAM College of Engineering and Technology. I will be working on the project "Classify Object Behavior to Enhance the Safety of Autonomous Vehicles" which will let me to enhance my existing knowledge of what I currently have about AI and its uses.