The Multi-Agent Autonomous Waste Collection System is a research-driven platform that employs multi-agent reinforcement learning to train individual waste-collecting robots to collaborate on route planning. Agents learn to avoid redundant coverage, minimize travel distance, and respond to dynamic waste generation patterns. Built in Python, the system integrates a simulation environment for testing and refining policies before real-world deployment. Users can configure map layouts, waste drop-off points, agent sensors, and reward structures to tailor behavior to specific urban areas or operational constraints.

The Multi-Agent-based Search and Rescue System in ROS is a robotics framework that leverages ROS for deploying multiple autonomous agents to perform coordinated search and rescue operations. Each agent uses onboard sensors and ROS topics for real-time mapping, obstacle avoidance, and target detection. A central coordinator assigns tasks dynamically based on agent status and environment feedback. The system can be run in Gazebo or on actual robots, enabling researchers and developers to test and refine multi-robot cooperation, communication protocols, and adaptive mission planning under realistic conditions.