AV4EV - Open-Source Autonomous Vehicle Software for Open-Standard Electric Vehicle Platforms

Mangharam, Rahul · 2024 · ROSA P / Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

The AV4EV project addresses the significant barriers in autonomous vehicle (AV) research, specifically the high cost and complexity of full-scale platforms versus the limited capabilities of small-scale remote-controlled cars. To bridge this gap, the authors developed an accessible, open-source, one-third-scale autonomous electric go-kart platform. This modular system is designed to provide universities and research institutions with a cost-effective tool for developing and testing advanced AV algorithms, including perception, localization, planning, and control, without the prohibitive expenses associated with full-sized vehicles. The platform integrates a modular mechatronic system comprising a power distribution system, main control system, throttle-by-wire, steer-by-wire, and electronic braking subsystems, all communicating via a Controller Area Network (CAN). It supports manual, teleoperated, and autonomous driving modes. The sensing suite includes an Ouster OS1 LiDAR, an OAK-D camera, a GNSS with real-time kinematic positioning for centimeter-level accuracy, and an IMU. The autonomous driving software is built on Robot Operating System (ROS2) and utilizes Python and C++. Key algorithms include a GNSS-based adaptive pure pursuit controller for pre-mapped racing, which employs min-curvature raceline optimization, and a camera-based follow-the-gap algorithm for reactive racing, which uses computer vision to detect track boundaries via grass detection and bird’s-eye view projection. Experimental validation demonstrated the platform’s effectiveness in both indoor and outdoor environments. The system successfully executed autonomous driving tasks with high performance in speed, accuracy, and reliability. Notably, the go-kart won the championship at the 2023 Autonomous Karting Series Purdue Grand Prix, competing against other national teams. The estimated cost for constructing the mechatronic system is approximately $12,500, and the sensing and software components cost around $11,000, significantly lower than full-scale alternatives. The platform’s modularity allows for customization and reusability, facilitating hands-on educational experiences and rapid prototyping. The significance of AV4EV lies in its ability to democratize AV research by lowering entry barriers for academic and commercial entities. By providing open-source hardware designs, software stacks, and comprehensive documentation, the project fosters collaboration and accelerates algorithmic advancements. The platform serves as a scalable solution for various applications, including logistics and urban mobility, and supports the development of an "Autonomy-as-a-Service" business model. The authors recommend expanding deployment use cases and increasing community engagement to further enhance the platform’s versatility and impact on the autonomous vehicle field.

Key finding

The AV4EV platform successfully demonstrates high-performance autonomous driving capabilities through modular hardware and open-source software, providing an accessible and cost-effective solution for academic research that bridges the performance gap between small-scale models and full-sized vehicles.

Methodology

field_study

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

StageOutcomeToolModelPromptAttemptsCompleted
discover success rosap 2 2026-05-23
archive success 1 2026-05-23
extract success cached 2 2026-06-10
clean success 1 2026-06-01
chunk success 1 2026-06-01
embed success 1 2026-06-02
enrich success 1 2026-05-23
promote success 1 2026-05-23
summarize success llm qwen3.6-27b-prismaquant summ-v5 3 2026-06-10
tag success vector_similarity 24 2026-06-11
verify success 2 2026-06-10

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).