NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education

@inproceedings{NeoRacer_26,
  title     = {{NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education}},
  author    = {Bandyopadhyay, Koneshka and Mehta, Ansh and El Mabsout, Bassel and Mancuso, Renato},
  year      = 2026,
  publisher = {arXiv},
  url       = {https://arxiv.org/pdf/2607.26855}
}

CopyDownload .bib

TY  - CONF
AU  - Bandyopadhyay, Koneshka
AU  - Mehta, Ansh
AU  - El Mabsout, Bassel
AU  - Mancuso, Renato
TI  - NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education
T2  - 
PY  - 2026
PB  - arXiv
AB  - While many existing fields in scientific domains depend on standard benchmarks for tackling research problems (e.g. Machine Learning), easing the burden of reviewing and reproducing various methods within the countless manuscripts, autonomous systems research has a significant lack of open, accepted, and prevalent hardware of use. Where standardization has appeared, the field has flourished. The issue presents itself poignantly in autonomous racing, as groups often build custom solutions, or buy niche and expensive research vehicles. Making applied control research, robotics research, and education untranslateable and difficult to compare. Furthermore, the expensive nature of such vehicles make exploration unavailable outside established labs with very significant resources. The nearest educational robots are affordable, but heavily underpowered and uninspiring. Thus, this work contributes the Neo- Racer, an open-source 1:12 scale autonomous racing platform designed to bridge this gap. Built around an NVIDIA Jetson Orin Nano (67 TOPS), a 270° LiDAR, a 120 fps global shutter camera, and a 9-axis IMU, NeoRacer ships pre-assembled and ready to use for $2,699, delivering over 3× the compute of comparable platforms at less than half the cost of the nearest pre-assembled alternative. NeoRacer is co-developed by the Neobotics Foundation and Seeed Studio and manufactured by Seeed Studio, pairing an open hardware and software design with scaled, repeatable production. The platform is designed to be modular and extensible, providing a standardized benchmarking environment for autonomous racing algorithms across institutions. We describe the hardware and software architecture, the design decisions informed by two pilot deployments (MIT IAP, 15 students; BU CPS Lab, 10 students), and the cost-performance tradeoffs that guided the platform’s development. NeoRacer hardware is licensed under CERN-OHL-S v2 and software under GPLv3, with all design files, firmware, and ROS2 software packages publicly accessible. arXiv:2607.26855v1 [cs.RO] 29 Jul 2026
ER  - 

CopyDownload .ris

%0 Conference Paper
%A Bandyopadhyay, Koneshka
%A Mehta, Ansh
%A El Mabsout, Bassel
%A Mancuso, Renato
%T NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education
%B 
%D 2026
%I arXiv
%X While many existing fields in scientific domains depend on standard benchmarks for tackling research problems (e.g. Machine Learning), easing the burden of reviewing and reproducing various methods within the countless manuscripts, autonomous systems research has a significant lack of open, accepted, and prevalent hardware of use. Where standardization has appeared, the field has flourished. The issue presents itself poignantly in autonomous racing, as groups often build custom solutions, or buy niche and expensive research vehicles. Making applied control research, robotics research, and education untranslateable and difficult to compare. Furthermore, the expensive nature of such vehicles make exploration unavailable outside established labs with very significant resources. The nearest educational robots are affordable, but heavily underpowered and uninspiring. Thus, this work contributes the Neo- Racer, an open-source 1:12 scale autonomous racing platform designed to bridge this gap. Built around an NVIDIA Jetson Orin Nano (67 TOPS), a 270° LiDAR, a 120 fps global shutter camera, and a 9-axis IMU, NeoRacer ships pre-assembled and ready to use for $2,699, delivering over 3× the compute of comparable platforms at less than half the cost of the nearest pre-assembled alternative. NeoRacer is co-developed by the Neobotics Foundation and Seeed Studio and manufactured by Seeed Studio, pairing an open hardware and software design with scaled, repeatable production. The platform is designed to be modular and extensible, providing a standardized benchmarking environment for autonomous racing algorithms across institutions. We describe the hardware and software architecture, the design decisions informed by two pilot deployments (MIT IAP, 15 students; BU CPS Lab, 10 students), and the cost-performance tradeoffs that guided the platform’s development. NeoRacer hardware is licensed under CERN-OHL-S v2 and software under GPLv3, with all design files, firmware, and ROS2 software packages publicly accessible. arXiv:2607.26855v1 [cs.RO] 29 Jul 2026

CopyDownload .enw

[
    {
        "id": "NeoRacer_26",
        "type": "paper-conference",
        "title": "NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education",
        "author": [
            {
                "family": "Bandyopadhyay",
                "given": "Koneshka"
            },
            {
                "family": "Mehta",
                "given": "Ansh"
            },
            {
                "family": "El Mabsout",
                "given": "Bassel"
            },
            {
                "family": "Mancuso",
                "given": "Renato"
            }
        ],
        "container-title": "",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "publisher": "arXiv",
        "abstract": "While many existing fields in scientific domains depend on standard benchmarks for tackling research problems (e.g. Machine Learning), easing the burden of reviewing and reproducing various methods within the countless manuscripts, autonomous systems research has a significant lack of open, accepted, and prevalent hardware of use. Where standardization has appeared, the field has flourished. The issue presents itself poignantly in autonomous racing, as groups often build custom solutions, or buy niche and expensive research vehicles. Making applied control research, robotics research, and education untranslateable and difficult to compare. Furthermore, the expensive nature of such vehicles make exploration unavailable outside established labs with very significant resources. The nearest educational robots are affordable, but heavily underpowered and uninspiring. Thus, this work contributes the Neo- Racer, an open-source 1:12 scale autonomous racing platform designed to bridge this gap. Built around an NVIDIA Jetson Orin Nano (67 TOPS), a 270° LiDAR, a 120 fps global shutter camera, and a 9-axis IMU, NeoRacer ships pre-assembled and ready to use for $2,699, delivering over 3× the compute of comparable platforms at less than half the cost of the nearest pre-assembled alternative. NeoRacer is co-developed by the Neobotics Foundation and Seeed Studio and manufactured by Seeed Studio, pairing an open hardware and software design with scaled, repeatable production. The platform is designed to be modular and extensible, providing a standardized benchmarking environment for autonomous racing algorithms across institutions. We describe the hardware and software architecture, the design decisions informed by two pilot deployments (MIT IAP, 15 students; BU CPS Lab, 10 students), and the cost-performance tradeoffs that guided the platform’s development. NeoRacer hardware is licensed under CERN-OHL-S v2 and software under GPLv3, with all design files, firmware, and ROS2 software packages publicly accessible. arXiv:2607.26855v1 [cs.RO] 29 Jul 2026"
    }
]

CopyDownload .json

K. Bandyopadhyay, A. Mehta, B. El Mabsout, and R. Mancuso, “NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education,” in , 2026.

CopyDownload .txt

Bandyopadhyay, K., Mehta, A., El Mabsout, B., & Mancuso, R. (2026). NeoRacer: An Open, Standardized 1:12 Scale Autonomous Race Car for Benchmarking and Education. In . arXiv.

CopyDownload .txt