v1.0.0-beta.4

What's new in this release

• Openrouter support for LLama and Anthropic: Added compatibility with OpenRouter API, enabling seamless access to more AI providers, including Meta’s LLaMA and Anthropic Claude models.
  This allows flexible model selection for natural language processing, reasoning, and control tasks depending on performance or cost preferences.
• Support multiple modes: We now support 5 different modes with Unitree Go2 full autonomy.
  • Welcome mode - Initial greeting and user information gathering
  • Conversation - Focused conversation and social interaction mode
  • Slam - Autonomous navigation and mapping mode
  • Navigation - Autonomous navigation mode
  • Guard - Patrol and security monitoring mode
• Support face blurring and detection: The OpenMind Privacy System is a real-time, on-device face detection and blurring module designed to protect personal identity during video capture and streaming.
  It runs entirely on the Unitree Go2 robot’s edge device, requiring no cloud or network connectivity.
  All frame processing happens locally — raw frames never leave the device. Only the processed, blurred output is stored or streamed.
  The module operates offline and maintains low latency suitable for real-time applications
• Support multiple RTSP inputs: The OpenMind RTSP Ingest Pipeline manages multiple RTSP inputs, supporting three camera feeds and one microphone input for synchronized streaming. The top camera feed is processed through the OpenMind face recognition module for detection, overlay, and FPS monitoring, while the microphone (default_mic_aec) handles audio capture and streaming. All processed video and audio streams are ingested through the OpenMind API RTSP endpoint, enabling multi-source real-time data flow within the system.
• Support echo cancellation and remote video streaming: Use our portal to remotely display your face in our dog backpack and talk to people directly.
• Support navigation and mapping: The Navigation and Mapping enables OM1 to move intelligently within its environment using two core modes: Navigation Mode and Slam Mode.
  In Slam Mode, the robot explores its surroundings autonomously, using onboard sensors to build and continuously update internal maps for spatial awareness and future navigation. This mode is typically used during initial setup or when operating in new or changing environments.
  In Navigation Mode, the robot travels between predefined points within an existing mapped area, leveraging maps generated in Slam Mode for path planning, obstacle avoidance, and safe movement to target locations.
• Refactor AI control messaging: We now use function calls for taking actions.
  Here's our new flow - Actions -> Function calls params -> LLM -> Function calls -> Json Structure (CortexOutputModel).
• Support Nvidia Thor: We now support Nvidia Thor for Unitree Go2 full autonomy.
• Added release notes to our docs: The official documentation now includes a dedicated Release Notes section, making it easier to track feature updates, improvements, and bug fixes over time. This also improves transparency for developers and users integrating new releases.
• Introducing Lifecycle
  Each operational mode in OM1 follows a defined lifecycle, representing the complete process from entry to exit of that mode. A mode lifecycle ensures predictable behavior, safe transitions, and consistent data handling across all system states.

What's Changed

• Create Media_server.mdx by @TangmereCottage in #401
• Add VLM Vila RTSP input and provider integration by @openminddev in #403
• Update submodule to fix RTSP connections by @openminddev in #408
• Update avatar by @openminddev in #410
• Stabilize the integration tests by @openminddev in #412
• Refactor AI control messaging to use AIStatusRequest and AIStatusResponse by @openminddev in #411
• Release notes by @Prachi1615 in #402
• simplified getting started guide by @Prachi1615 in #407
• Add spatial memory by @openminddev in #400
• Add location volume by @openminddev in #413
• Update om1-modules by @openminddev in #415
• Add provider for teleops conversation by @YuchengZhou821 in #422
• Support Near AI by @openminddev in #424
• updated docs for audio config by @Prachi1615 in #427
• Add venv to image by @openminddev in #434
• Replace the json structure output with function calls by @openminddev in #433
• update supported models docs by @Prachi1615 in #437
• feat: add face presence provider/input and test example by @WenjinFu in #436
• Add mode system by @openminddev in #439
• Update full autonomy docs by @Prachi1615 in #432
• Fix audio path by @openminddev in #450
• Openrouter support by @Prachi1615 in #431
• Feat/hello mode by @WenjinFu in #446
• Update default entry and internet check by @openminddev in #452
• Install iputils-ping to allow the om1 to ping the internet by @openminddev in #453
• added navigation integeration by @jerinpeter in #445
• Fix bugs for unitree_go2_modes by @openminddev in #457
• updated the llm prompt and gallery status by @WenjinFu in #464
• added amcl localization input by @jerinpeter in #458
• Add TTS control by @openminddev in #468
• updated navigation with tts feedback by @jerinpeter in #469
• Improve guard mode by @openminddev in #475
• Fix motor_speed setter validation in RPLidar driver by @sohw400 in #478
• update support email by @Prachi1615 in #486
• change to get recent seconds faces to llm by @WenjinFu in #488
• Introduce lifecycle by @openminddev in #477
• Fix: Add multilingual support for Google ASR including Korean by @sohw400 in #461
• Support Nvidia Thor by @TangmereCottage in #438
• Add reviewer rules by @openminddev in #546
• Fix reviewer rules by @openminddev in #547
• Add more rules for tag by @openminddev in #548

New Contributors

• @YuchengZhou821 made their first contribution in #422
• @WenjinFu made their first contribution in #436
• @jerinpeter made their first contribution in #445
• @sohw400 made their first contribution in #478

Full Changelog: v1.0.0-beta.3...v1.0.0-beta.4