Long-Range Autonomous Off-Road Driving System
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Courant Institute of Mathematical Sciences
- Organisation type
- Academia
- Country
- United States of America
- Published
- 8 January 2009
- Authors
- Raia Hadsell, Pierre Sermanet, Jan Ben, Ayse Erkan, Marco Scoffier, Koray Kavukcuoglu, Urs Muller, Yann LeCun
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Robotics, Driving
- Task
- Self-driving car
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 12.4K
- Training data
- 450,000 tokens
- Epochs
- 30
C1: 20x7x6 C3: 369x6x5 F4: 100x5 "This particular network has two convolutional layers and one subsampling layer. The first convolutional layer has 20 7 × 6 filters, and the second layer has 369 6 × 5 filters. The layers are not fully connected; in particular, the Y, U, and V filters are kept separate throughout the two layers. For the purposes of training, a final 100-component, fully connected layer is trained with five outputs"
"The training set contained 450,000 labeled image patches"
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 2.8 × 10¹⁴ FLOP
- How it was established
- Operation counting
Every filter is only connected to ⅓ of the input channels: “The layers are not fully connected; in particular, the Y, U, and V filters are kept separate throughout the two layers.” The text of the paper and Figure 7 don’t match, the text mentions an additional D=369 convolutional layer that is not represented in the Figure Input: 12*25 1st CNN: 2*12*25*(3/3)*7*6*20=240000 Size after layer: 6*20*20 Size after pooling layer (1x4): 6*5*20 2nd CNN: 2*6*5*(20/3)*6*5*369=4428000 FC: 2*6*5*369*100=2214…
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Learning long‐range vision for autonomous off‐road driving
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Long-Range Autonomous Off-Road Driving System was published by Courant Institute of Mathematical Sciences, in United States of America, in January 2009. It comes out of academia.
It works in Vision, Robotics, Driving, and is recorded as doing self-driving car.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
Training it took roughly 2.8 × 10¹⁴ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
Around 450,000 tokens went into training it.
Answers
Long-Range Autonomous Off-Road Driving System — common questions
Who created Long-Range Autonomous Off-Road Driving System?
Long-Range Autonomous Off-Road Driving System was published by Courant Institute of Mathematical Sciences, based in United States of America, categorised as academia.
When was Long-Range Autonomous Off-Road Driving System released?
Long-Range Autonomous Off-Road Driving System was published in January 2009. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Long-Range Autonomous Off-Road Driving System used for?
Long-Range Autonomous Off-Road Driving System works in Vision, Robotics, Driving, and is recorded as handling self-driving car. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train Long-Range Autonomous Off-Road Driving System?
Around 2.8 × 10¹⁴ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
What GPU do I need to run Long-Range Autonomous Off-Road Driving System?
None. Long-Range Autonomous Off-Road Driving System is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is Long-Range Autonomous Off-Road Driving System open source?
No. Long-Range Autonomous Off-Road Driving System has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Long-Range Autonomous Off-Road Driving System have?
Long-Range Autonomous Off-Road Driving System has 12.4K parameters. C1: 20x7x6 C3: 369x6x5 F4: 100x5 "This particular network has two convolutional layers and one subsampling layer. The first convolutional layer has 20 7 × 6 filters, and the second layer has 369 6 × 5 filters. The layers are not fully connected; in particular, the Y, U, and V filters are kept separate throughout the two layers. For the purposes of training, a final 100-component, fully connected layer is trained with five outputs". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.