Agentic Robotics Control
This challenge focuses on developing an advanced agentic control system for a simulated humanoid robot. You will use AutoGen to orchestrate a team of specialized agents, each responsible for different robotic sub-systems (e.g., perception, locomotion, manipulation). The system must demonstrate robust task execution, adaptability to dynamic environments, and adhere to safety protocols using constitutional AI principles. It will integrate Gemini 3 Pro for deep reasoning and code generation for complex actions, and OpenAI GPT 5.2 for fast, reactive decision-making via MCP tool calls to a simulated robot API.
What you are building
The core problem, expected build, and operating context for this challenge.
This challenge focuses on developing an advanced agentic control system for a simulated humanoid robot. You will use AutoGen to orchestrate a team of specialized agents, each responsible for different robotic sub-systems (e.g., perception, locomotion, manipulation). The system must demonstrate robust task execution, adaptability to dynamic environments, and adhere to safety protocols using constitutional AI principles. It will integrate Gemini 3 Pro for deep reasoning and code generation for complex actions, and OpenAI GPT 5.2 for fast, reactive decision-making via MCP tool calls to a simulated robot API.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Orchestrate a role-based agent team using AutoGen for simulated humanoid robot control, including a Task Planner, Perception Processor, Action Executor, and Safety Monitor agents.
Implement hybrid instant/deep reasoning patterns: utilize OpenAI o3 for rapid, reactive decision-making in safety-critical situations or simple commands, and Gemini 3 Pro (with Deep Think mode) for complex task planning, code generation for new actions, and problem-solving.
Design and integrate constitutional AI guards within agent prompts and post-processing to ensure all robotic actions adhere to predefined safety and ethical guidelines.
Leverage Semantic Kernel for managing high-level mission planning, enabling agents to decompose complex goals into actionable steps and orchestrate MCP tool calls.
Build MCP-enabled tools that simulate a robot's API (e.g., 'move_joint', 'sense_environment', 'grasp_object'), allowing agents to interact with the simulated robot environment.
Implement A2A protocol within AutoGen for seamless communication and collaboration between specialized robot control agents, ensuring coordinated action.
Develop error handling and recovery mechanisms, allowing the agent system to adapt to unexpected events in the simulated environment and safely re-plan.
Explore Marvin for ensuring structured and reliable output from LLMs for robot commands and state updates.
[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsAI Research & Mentorship
Participation status
You haven't started this challenge yet
Operating window
Key dates and the organization behind this challenge.
Find another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.