Self-Driving Delivery Agent

Visit Tool

Self-Driving Delivery Agent is an open-source project that enhances LLM-based autonomous driving agents with embodied and social experiences. It provides an official implementation of the DriVLMe paper for research and development.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is Self-Driving Delivery Agent?

Self-Driving Delivery Agent, also known as DriVLMe, is an open-source project providing the official implementation of the IROS 2024 paper: "Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experience." This tool is designed for researchers and developers working on autonomous driving systems, particularly those interested in integrating large language models (LLMs) with real-world driving experiences. It offers a framework for setting up a conda environment, preparing LLaVA weights, and training/finetuning models on datasets like bddx and SDN. The project includes scripts for pretraining, finetuning, and evaluating autonomous driving agents, making it a valuable resource for advancing the field of AI-driven autonomous vehicles.

Best used for

Ideal for professors and researchers who need to implement and evaluate advanced LLM-based autonomous driving agents. Especially valuable for those working on embodied and social experiences in self-driving systems, offering a robust framework for training, finetuning, and evaluating models using real-world datasets.

Common actions

develop autonomous agents

train driving models

evaluate AI performance

"AI Agents"face swappinggithub copilotlow-code/no-codeautomated workflowopen-sourceworkflowsdeepfakecollaboration

Capabilities

Key features

LLaVA weights integration
BDDX dataset pretraining
SDN dataset finetuning
Open-loop evaluation
Physical action accuracy

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What is the primary purpose of the DriVLMe project?

The DriVLMe project provides the official implementation for the IROS 2024 paper "Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experience." Its main goal is to offer a framework for researchers to develop and evaluate autonomous driving agents using large language models.

What are the main datasets used for training and finetuning in DriVLMe?

DriVLMe utilizes the bddx dataset for pretraining and the SDN dataset for finetuning. These datasets are crucial for enhancing the LLM-based autonomous driving agents with embodied and social experiences, providing diverse scenarios for model development.

What are the hardware requirements for running DriVLMe?

The project recommends training on 4 A40 GPUs for both pretraining on the bddx dataset and finetuning on the SDN dataset. This indicates that significant computational resources are needed for optimal performance and model training.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI General-Purpose Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Also listed in

This tool also appears in

Research & Education › Academic Research Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce