{"id":46212304,"url":"https://github.com/larsll/deepracer-pi","last_synced_at":"2026-03-03T09:18:52.250Z","repository":{"id":220856547,"uuid":"752770973","full_name":"larsll/deepracer-pi","owner":"larsll","description":"A port of the DeepRacer software stack for the Raspberry Pi 4.","archived":false,"fork":false,"pushed_at":"2024-04-10T18:08:35.000Z","size":976,"stargazers_count":2,"open_issues_count":0,"forks_count":4,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-04-10T21:49:30.109Z","etag":null,"topics":["deepracer","raspberry-pi","robotics","ros2"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/larsll.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2024-02-04T18:57:30.000Z","updated_at":"2024-04-14T19:41:11.229Z","dependencies_parsed_at":"2024-02-07T07:31:04.558Z","dependency_job_id":"3d66dccc-97bf-411c-91ab-c27a92939b2b","html_url":"https://github.com/larsll/deepracer-pi","commit_stats":null,"previous_names":["larsll/deepracer-pi"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/larsll/deepracer-pi","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larsll%2Fdeepracer-pi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larsll%2Fdeepracer-pi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larsll%2Fdeepracer-pi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larsll%2Fdeepracer-pi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/larsll","download_url":"https://codeload.github.com/larsll/deepracer-pi/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/larsll%2Fdeepracer-pi/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30038945,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-03T06:58:30.252Z","status":"ssl_error","status_checked_at":"2026-03-03T06:58:15.329Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deepracer","raspberry-pi","robotics","ros2"],"created_at":"2026-03-03T09:18:51.817Z","updated_at":"2026-03-03T09:18:52.242Z","avatar_url":"https://github.com/larsll.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"The effort has moved to [DeepRacer Custom](https://github.com/aws-deepracer-community/deepracer-custom)!\n\n# DeepRacer for Raspberry Pi 4\n\nThis repository provides a port of the DeepRacer software stack to the Raspberry Pi 4. It runs\non Ubuntu 22.04 with ROS2 Humble, but with most of original code. To make the image smaller the server image is recommended.\n\n## Features\n\nMain features of the port:\n\n- Previously trained models will work\n- Uses Tensorflow Lite or OpenVINO for inference. Supports the Intel Neural Compute Stick 2 (NCS2/MYRIAD)\n- Can integrate with DREM\n- Single power source¹ - reduces weight and lowers center of gravity\n- Over-the-Air Software Updates\n\n## Parts\n\nThe following parts are needed:\n\n- Raspberry 4 or compatible board, recommended 4GB or 8GB RAM, but even 1GB will work as memory consumption is about 700MB.\n- Optional: [Intel Neural Compute Stick (NCS) 2](https://www.intel.com/content/www/us/en/developer/articles/tool/neural-compute-stick.html)\n- [Waveshare Servo Driver Hat](https://www.waveshare.com/product/raspberry-pi/hats/motors-relays/servo-driver-hat.htm) or compatible PCA9865 servo boards.\n- USB camera with ~60 deg FOV, e.g. original DeepRacer camera or a Raspberry Pi camera.\n- 4 RGB light diodes\n- Misc cables\n\n¹ The Waveshare hat comes with a step-down converter from 7.4V to 5V, and will power the Pi via the GPIO header. Other similar cards will require separate power.\n\n**Optional**\n\n- Fan/heat-sink kit for Raspberry PI 4\n\n## Software Install\n\nInstallation of software is reasonably straight forward, as pre-built packages are provided:\n\n- Flash an SD card with Ubuntu 22.04 Server for ARM64 using the Raspberry Pi Imager.\n- Boot the SD card, and let it upgrade (this takes some time...)\n- Run `git clone https://github.com/larsll/deepracer-pi`\n- Run `sudo ./install-prerequisites.sh`\n- Reboot\n- Run `sudo ./install-deepracer.sh`\n\nOnce installed you can start the stack with `sudo /opt/aws/deepracer/start_ros.sh`. To ensure a smooth start a camera needs to be plugged in.\nThe launch log will now display in the console.\n\nTo automatically start at boot do `sudo systemctl enable deepracer-core` and to start the service in the background `sudo systemctl start deepracer-core`.\n\n### Changes\n\nSome changes have been made to the code to enable access to GPIO as sysfs layout is different on the Raspberry Pi than on the custom Intel board.\n\n\n### Improvements\n\n- Stripped down OS\n- Runs the custom deepracer stack also seen in [deepracer-scripts](https://github.com/davidfsmith/deepracer-scripts).\n\n### Details\n\n**PWM Outputs**\n\n| Channel | Purpose          | Notes                                                                   |\n| ------- | ---------------- | ----------------------------------------------------------------------- |\n| 0       | Speed controller | \u003cspan style=\"color:red\"\u003eRemove red cable for stock DeepRacer ESC\u003c/span\u003e |\n| 1       | Steering servo   |                                                                         |\n| 2       | RGB LED          | Tail light - Red                                                        |\n| 3       | RGB LED          | Tail light - Green                                                      |\n| 4       | RGB LED          | Tail light - Blue                                                       |\n| 5       |\n| 6       |\n| 7       | RGB LED          |\n| 8       | RGB LED          |\n| 9       | RGB LED          |\n| 10      | RGB LED          |\n| 11      | RGB LED          |\n| 12      | RGB LED          |\n| 13      | RGB LED          |\n| 14      | RGB LED          |\n| 15      | RGB LED          |\n\n\u003cspan style=\"color:red\"\u003e**NOTE:** Remove the red cable on the stock DeepRacer from the speed controller into PWM channel 0, otherwise you are putting 6V into the servo hat.\u003c/span\u003e\n\nLiPo can power both the board and car, 3 pin (balance lead) gets wired to VIN (black and red cables only) to power the board and RPi. The 2 pin power cable goes to the car as normal.\n\n\n**GPIO layout:**\n\n- `gpio1` - enables PWM (does not do anything, PWM is always on for the Waveshare board)\n- `gpio495`-`gpio504` - maps to PWM7 to PWM15 on the Hat, to control three RGB leds (those originally on the side of the board)\n\n**USB host mode:**\nTo connect the USB-C port on the Raspberry Pi 4 to a USB on your computer, then you need to perform two changes:\n* Add `dtoverlay=dwc2,dr_mode=host` to your `/boot/firmware/config.txt`\n* Add `modules-load=dwc2,g_ether` to your `/boot/firmware/cmdline.txt`\n\nWith this you will see a new network connect appear in Windows (and Mac?). The Raspberry Pi will have IP 10.0.0.1; you can connect to the console via `https://deepracer.aws`. This will require your computer to be disconnected from all other networks (given a DNS priority issue). SSH directly to the IP will work.\n\n## What does not (yet) work\n\n- Battery gauge is not connected - red warning message persists\n- Device Info Node is looking in non-existent places - no real impact\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flarsll%2Fdeepracer-pi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flarsll%2Fdeepracer-pi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flarsll%2Fdeepracer-pi/lists"}