← Projects

Fetcherbot Agentic ROS

ROSGazeboAgenticTB3college projectAI for RoboticsGitHub ↗

Architecture

                        ┌─────────────────────────────┐
                        │         LLM Agent            │
                        │  (Groq Llama 3.3-70B,        │
                        │   LangGraph state machine)   │
  Voice / Text ───────► │                              │
                        │  - Reasons about the task    │
                        │  - Picks tools by phase      │
                        │  - Handles failures          │
                        │  - Sequences waypoints       │
                        └────────────┬─────────────────┘
                                     │
            ┌────────────┬───────────┼───────────┬──────────────┐
            │            │           │           │              │
       scan_scene  navigate_to  check_nav   pick_up      go_to_checkpoint
            │            │           │           │              │
          YOLO11       Nav2     (event-driven)  arm +          named
       + ground-                              gripper          pose
         plane                                actions          dict
        projection                          (scripted)
            │            │                      │
         Gazebo       Gazebo                 Gazebo
         Camera        Base                    Arm

Tech Stack

LayerTool
RobotTurtleBot3 Waffle Pi + OpenManipulator-X (4-DOF)
SimulatorGazebo Classic 11
ROS VersionROS 2 Humble
Object DetectionYOLO11 (imgsz=1280)
3D Localizationimage_geometry ground-plane projection + tf2
NavigationNav2 (NavfnPlanner + DWBLocalPlanner) + slam_toolbox
Manipulationros2_control FollowJointTrajectory + GripperCommand; MoveIt2 wired (IK use TBD)
LLM AgentGroq Llama 3.3-70B via LangGraph
Agent ToolsPython functions wrapped as LangGraph tools, calling ROS