End to End Learning for Self-Driving Cars · HackerPapers discussions

End to End Learning for Self-Driving Cars — mentioned by Isinlor

Wed, 18 Jul 2018 13:44:53 GMT

I'm curious why author decided to completely disregard reinforcement learning. "Note that neural nets are neither. There has been a relatively small amount of non-mainstream work of getting neural nets to control very simple robots, mostly in simulation only." This is just plain false. Playing Arcade Games involves controlling an agent and there is a lot of widely published, very mainstream work from DeepMind, OpenAI and many other less known research groups. The big part of hype is about using deep neural networks in tandem with reinforcement learning. It's a very reactive system. In complex…

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — HN submission

Sat, 07 Jul 2018 22:22:27 GMT

Ask HN: What makes a good autonomous vehicles engineer?

There are a lot of aspects behind the science of autonomous vehicles such Computer vision, perception, motion planning, and control, .. etc. However, making it to this industry is still not clear to many of engineers. I have some papers such `End to End Learning for Self-Driving Cars` https://arxiv.org/pdf/1604.07316.pdf, but I hope that one of the autonomous vehicles engineers chime in and describe what it takes to enter this industry. What are the skills needed to be hired. Is Drivelss cars Nano-degree helpful ?

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by edshiro

Fri, 25 May 2018 14:53:34 GMT

NVidia published a very interesting paper on this technique called "End-To-End Learning For Self-Driving Cars": https://arxiv.org/abs/1604.07316 . It's an enjoyable read. The car learns to steer itself on an empty road. It's a good experiment to witness the power of deep learning and neural nets. For autonomous vehicles though, you need much more than that (e.g. sensor fusion, obstacle detection, localization, behaviour prediction, trajectory prediction, path planning, motion control, etc.).

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by edshiro

Fri, 25 May 2018 14:46:17 GMT

The steering angles are probably automatically obtained from the script you run when manually training the toy vehicle. I presume at every frame an image is captured along with the steering angle for this image. You then create a neural net architecture that is being fed images and steering angle positions and outputs steering angle predictions. This is a regression problem that can be expressed in plain English as: "First train the neural network with a collection of images and associated steering angles. After training, if I were to give the neural network a new image it has never seen…

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by imgyuri

Sat, 16 Sep 2017 15:47:08 GMT

In terms of capturing the screen input for training, the fps is capped at 10 fps. This is following the number suggested in NVIDIA's paper[1], which cautions against overfitting. The program captures faster when the steering angle gets larger, because it suggests that curvy road is ahead, which are the more challenging scenarios for the program. In terms of testing, the max fps is determined by the performance of the GPU and the complexity of the model. I couldn't find any definitive studies done on the matter, but anywhere from 10-30 fps seems to work OK. [1] https://arxiv.org/abs/1604.07316

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by cr0sh

Wed, 21 Jun 2017 16:42:51 GMT

I think LIDAR will have a place, if they can get the per-sensor cost down to something reasonable (under $500.00 per sensor, for 3D 180 degree with at least 32 vertical res beams - or the equivalent). But I think first we'll see cars utilizing tech as described in this paper: https://arxiv.org/abs/1604.07316 ...and variations of it to handle other modeling and vision tasks. Self-driving vehicle systems are amazing complex; it won't ultimately be any single system or sensor, or piece of software or algorithm that solves the problem - it's going to be a complex mesh of all of them working in…

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by cr0sh

Wed, 10 May 2017 21:04:18 GMT

I doubt anything like that would happen. While Tesla Motors was founded prior to the creation of the Tesla GPU architecture, there's not really any overlap - in fact, I wouldn't be surprised if Tesla Motors wasn't using something like this from NVidia: http://www.nvidia.com/object/drive-px.html As far as any overlap software-wise is concerned, while it isn't super clear what Tesla Motors is doing for their self-driving systems, based on what I've seen it seems like they are using only "basic" lane-detection and identification along with some other algorithmic vision-based systems. I'm not…

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by cr0sh

Wed, 15 Feb 2017 21:41:54 GMT

I can understand why it probably isn't on the list yet (not as many citations, since it is fairly new) - but NVidia's "End to End Learning for Self-Driving Cars" needs to be mentioned, I think: https://arxiv.org/abs/1604.07316 https://images.nvidia.com/content/tegra/automotive/images/20... I implemented a slight variation on this CNN using Keras and TensorFlow for the third project in term 1 of Udacity's Self-Driving Car Engineer nanodegree course (not special in that regard - it was a commonly used implementation, as it works). Give it a shot yourself - take this paper, install TensorFlow…

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — mentioned by tansey

Thu, 21 Jul 2016 03:08:05 GMT

> The data is useless unless it is annotated (e.g. a human labels where the lanes are, where the obstacles are, what the bicylist is doing, etc.) - that's the bottleneck, not collecting large amounts of raw sensor data + driver actions. Except that is exactly what Nvidia did, and it worked out fine for them: https://arxiv.org/abs/1604.07316

Paper and discussion history. A mention is not an endorsement.

End to End Learning for Self-Driving Cars — HN submission

Wed, 27 Apr 2016 13:23:38 GMT

End to End Learning for Self-Driving Cars [pdf]

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

End to End Learning for Self-Driving Cars — HN submission

Wed, 27 Apr 2016 01:34:58 GMT

ConvNet-Based “End to End Learning for Self-Driving Cars”

13 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

End to End Learning for Self-Driving Cars — HN submission

Tue, 26 Apr 2016 19:43:21 GMT

End to End Learning for Self-Driving Cars

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.