UC Berkeley Capstone Project

Search & Rescue Robot

ROSMaster aims to create an autonomous robot capable of navigating disaster-like environments, locating survivors, and returning to retrieve them without putting human responders at risk. The project uses a small mobile rover as a platform to explore how robotics can support faster, safer, and more reliable search-and-rescue missions in real-world scenarios.

Solution

Mapping

The LiDAR allows the system to understand the surrounding environment. With this information, the robot can determine the layout of the room as well as know where the robot is within that space.
Navigation

With the map, the robot can patrol the entire area, navigating through the space while continuously updating its surroundings. In disaster scenarios, it’s crucial that the robot can avoid obstacles as it moves through the environment.
Image Detection

The front-facing camera is used to detect survivors, providing information about who they are and where they’re located. In our prototype, we use identifiable tags to simulate survivor detection and simplify image recognition.
Rescue Tool

Using our custom electromagnetic arm, the robot can grab survivors and transport them to safety. For this proof of concept, we use magnetic dolls, making the retrieval process simple and focus on validating the rescue workflow.