Leobardo Campos is a Research Scientist in the Intelligence Systems Research lab at Intel Labs where he focuses on enabling better human-robot collaboration.
Highlights:
- Intel Labs research scientist Leobardo Campos was awarded the 2022 Weizmann Award for technology and engineering from the Mexican Academy of Sciences for his thesis work on “Autonomous Navigation of MAVs in Unknown Cluttered Environments.”
- Campos’ work presents an autonomous navigation framework for reaching a goal in unknown three‐dimensional cluttered environments.
- The novel method outperforms state-of-the-art methods in success rate when navigating a random forest and achieves a much faster mapping time on other tasks.
Intel Labs research scientist Leobardo Campos was awarded the 2022 Weizmann Award for technology and engineering from the Mexican Academy of Sciences for his work on “Autonomous Navigation of MAVs in Unknown Cluttered Environments.” The Weizmann award is a nationally recognized honor granted to exceptional doctoral theses carried out in Mexico, in the areas of exact sciences, natural sciences, and engineering and technology. Submissions are evaluated by a jury made up of the AMC Awards Commission, which considers the originality of the work, its rigor, and its scientific importance. On winning the award, Campos said, “the best part is that now a lot of people can read my thesis.”
A visit to the Intel Guadalajara Design Center. From left: Rodrigo, Tony, Adan, Hector, Edgar, Paul Werbos, Julio, Paulo and Leo Campos.
Recently, there have been many advances in the algorithms required for autonomous navigation in unknown environments, such as mapping, collision avoidance, trajectory planning, and motion control. These components have been integrated into drones with high‐end computers and graphics processors. However, further development is required to enable compute‐constrained platforms with such autonomous navigation capabilities. That is where Campos' work comes into play; in his thesis, Campos and his team present an autonomous navigation framework for reaching a goal in unknown three‐dimensional cluttered environments. The “secret sauce” of this framework lies in the tight integration of its three main components:
- A computationally efficient method for mapping the environment from the disparity measurements obtained from a depth sensor.
- A stochastic approach to generate a path to a given goal, taking into account the field of view constraints on the space that is assumed to be safe for navigation.
- A fast algorithm for the online trajectory generation, taking into account the robot's dynamic constraints, model and environmental uncertainty, and disturbances.
“The main idea was to enable small robots with low computing power and small sensing capabilities to be truly autonomous, meaning that you can give the robot a goal, and it can navigate and achieve that goal without knowledge of the map or the environment,” said Campos.
When testing the performance of the algorithm on the task of navigating in a random forest, Campos and his team found that their work outperformed state-of-the-art (SOTA) methods in success rate, especially as tree density increased. The researchers’ tests found that the novel method was capable of changing direction and determining an alternative path when faced with obstacles. Furthermore, when it comes to computation, the algorithm can map over 10 times faster than SOTA methods, achieving a mapping time of 0.256 ms compared to 2.035 ms and 700.7 ms. Watch the navigation algorithm in action below:
Campos attributes a large portion of the project’s success to Intel. During his doctorate program, Campos was also working at Intel Labs in Mexico, and when asked about that time, he said, “I had to take lectures from the university, then come here and work for Intel applying the code and the algorithms and making the test. It was really a challenge, but it was an important challenge to me, and I'm pretty sure that this award couldn't even be possible without Intel's help. Thanks to Intel, I had access to a high-end laboratory with a 3D printer, motion capture systems, drones, cameras, and all the computing power that you could need. From there, it was just up to me to use all of those tools to the best of my ability.”
Making an Impact
According to Campos, this innovative technology has the building blocks to enable a robot to perform search and rescue in a disaster scenario, and he is excited at the prospect of seeing his technology make a difference in the world. In fact, the widespread adoption of his algorithm is one dream that keeps him motivated in his work:
“I think there is a very small number of companies that can make an impact in day-to-day life for people, and Intel is one of those companies. I have a dream for all the robots in the world to be executing an algorithm that I designed, and I think that Intel is a very good place to reach that dream. For example, the USB connector was developed as a part of a project at Intel, and maybe someday a robotics algorithm can reach that level of implementation.”
Scott Bair is a Senior Technical Creative Director for Intel Labs, chartered with growing awareness for Intel’s leading-edge research activities, like AI, Neuromorphic Computing and Quantum Computing. Scott is responsible for driving marketing strategy, messaging, and asset creation for Intel Labs and its joint-research activities. In addition to his work at Intel, he has a passion for audio technology and is an active father of 5 children.
Scott has over 23 years of experience in the computing industry bringing new products and technology to market. During his 15 years at Intel, he has worked in a variety of roles from R&D, architecture, strategic planning, product marketing, and technology evangelism. Scott has an undergraduate degree in Electrical and Computer Engineering and a Masters of Business Administration from Brigham Young University.