Title: Next Generation Explorers: Robotic Systems Enabling Autonomous Exploration
Carnegie Mellon University’s Robotics Institute is at the forefront of developing the next generation of explorers—robots. The Autonomous Exploration Research Team has successfully created a suite of robotic systems and planners that empower robots to explore unknown environments at a faster pace, navigate even the darkest corners, and generate detailed and accurate maps. The remarkable part is that these systems operate autonomously, without requiring human intervention.
Exploring the Unknown with Autonomous Robots:
The Autonomous Exploration Research Team has been tirelessly developing exploration systems for over three years. Their robots have successfully explored and mapped various locations such as underground mines, parking garages, the Cohon University Center, and both indoor and outdoor areas on the CMU campus. With computers and sensors that can be easily attached to any robotic platform, these systems have transformed robots into modern-day explorers. Notably, motorized wheelchairs and drones have been utilized extensively for testing purposes.
Three Modes of Exploration:
The group’s systems enable robots to explore in three distinct modes. In the first mode, an individual can control the robot’s movements and direction, while autonomous systems ensure the robot avoids collisions. In the second mode, users can select a point on the map, and the robot will navigate autonomously to that designated location. Finally, the third mode is pure exploration, with the robot independently investigating the entire space and creating a comprehensive map.
Enhanced Features and Capabilities:
The team integrated a 3D scanning lidar sensor, a forward-looking camera, and an inertial measurement unit sensor with an advanced exploration algorithm. This combination allows robots to determine their precise location, track their previous locations, and plan their next move effectively. Notably, these new systems offer substantial improvements compared to previous approaches. They generate more complete maps in less time, reducing the algorithm run time by half.
Exploring Challenging Environments:
The upgraded systems excel in low-light and challenging conditions where communication is limited, including caves, tunnels, and abandoned structures. Team Explorer, powered by the group’s exploration system, participated in DARPA’s Subterranean Challenge and achieved remarkable success. Although the team placed fourth overall, they won the Most Sectors Explored Award for mapping the largest portion of the route among all competing teams.
The Autonomous Exploration Research Team strongly believes in open-sourced collaboration. They eagerly share their work, aiming to strengthen society’s capabilities in building autonomous exploration robots. Chao Cao, a Ph.D. student in robotics and the lead operator for Team Explorer, emphasizes that this capability is fundamental and holds immense potential for various applications, from delivery services to search-and-rescue missions.
Without a doubt, autonomous exploration robots powered by the research group’s developments have immense potential. By harnessing the capabilities of these advanced robotic systems, society can experience groundbreaking advancements in multiple domains. Watch the video to witness the extraordinary achievements of these next-generation explorers.