Helping robots follow a new path

ASU Regents Professor Ying-Cheng Lai leads machine learning research enabling robots to traverse flexible, complex trajectories


October 12, 2023

​While science fiction movies depict robots moving freely on their own, sometimes running to avoid perilous explosions or collapsing buildings, today’s technology doesn’t have that capability — yet.

Ying-Cheng Lai, an ASU Regents Professor of electrical engineering in the Ira A. Fulton Schools of Engineering at Arizona State University, his doctoral students and two collaborators from the U.S. Army DEVCOM Army Research Laboratory have moved fantasy one step closer to reality with their new method for programming robots’ movements. A robotic hand points to coordinates in a virtual environment. Ying-Cheng Lai, an ASU Regents Professor of electrical engineering in the Ira A. Fulton Schools of Engineering at Arizona State University, worked with his students and collaborators from the U.S. Army DEVCOM Army Research Laboratory to use a type of machine learning called reservoir computing to control the movement of two robotic arms in complex trajectories in a simulation. Graphic by Erika Gronek/ASU, Adobe Firefly Download Full Image

Lai led a research team in the use of reservoir computing, a type of machine learning, to program a robot to move two arms on a 2D plane in a computer simulation. This method allows the robot to change trajectory between predefined paths with only partial knowledge of the surrounding environment.

“The innovative aspect of this approach lies in its capacity to operate effectively with only partial observation of the state of the system, in contrast to the traditional requirement of comprehensive knowledge about the robot and its environment,” Lai says. “It is akin to attempting to solve a jigsaw puzzle by focusing solely on a few pieces rather than the complete image.”

Robots’ movements are traditionally programmed using a mathematical function-based machine learning method known as linear quadratic tracking, which requires in-depth knowledge about both the machine and its environment. Frequent time-consuming and finicky recalibration are required, limiting the effectiveness of movement programming and prohibiting on-the-fly trajectory changes sometimes necessary for robots to avoid obstacles in their paths.

Lai says this new research, supported by the U.S. Air Force Office of Scientific Research and the U.S. Army Research Office, focuses on enabling a breakthrough steppingstone to unlock potential applications in autonomous drones and ships, devices to aid humans in performing certain tasks, laser cutting tools to create complicated shapes and more.

The science journal Nature Communications has published the research findings in the team’s paper “Model-free tracking control of complex dynamical trajectories with machine learning.”

Rewriting robot movement programming

The shortcomings of linear quadratic tracking motivated Lai and his team to seek new solutions for robot control.

“Linear quadratic tracking is like attempting to teach a pet dog various tricks, relying solely on one type of treat for each trick,” he says. “Such an approach may have limited applications due to its lack of flexibility.”

The research team set out to use partial observations of the system’s state, which requires the robot to learn from its memory of previous experiences. Ultimately, Lai and his collaborators chose to focus on a technique called reservoir computing because of its ability to instill memory that gives a system learning ability.

Reservoir computing allows a system to correlate its training inputs to outputs and analyze what outputs work best to achieve the system’s programmed goal. Lai compares reservoir computing to the distinct ways ripples interact with each other in a pond depending where and how forcefully stones are thrown into the water.

“If we observe the ripples carefully, we may be able to tell where and how hard the stones were thrown, even without seeing the actual throwing process,” Lai says.

“We can relate the pond to the ‘reservoir,’ or memory, in reservoir computing, where the dynamic system reacts to and interprets inputs, which are similar to the stones thrown into the pond. The way the reservoir reacts to these inputs can be analyzed to make sense of the input or even predict future inputs.”

Reservoir computing’s adaptability makes it well suited to the research of Lai and his team, which includes electrical engineering doctoral students Mohammadamin Moradi and Zheng-Meng Zhai. With fine-tuning and further experimentation, the team achieved its goal of controlling two simulated robotic arms in any trajectory, along with the ability to switch to another desired path without prior notice.

A significant learning experience for students

For Zhai, the research paper’s primary author, the work represents a significant accomplishment of his doctoral thesis project.

Zhai performed the project’s computations and ran its simulations, in addition to drafting the paper summarizing the investigation’s findings. He says the experience even inspired him to pursue a potential career path in academia.

“Through this research, I mastered advanced analytical techniques in nonlinear dynamics and became more familiar with control theory,” Zhai says. “After this successful outcome, maybe I will do more work in machine learning control and try to be a professor in the future.”

Moradi, the research paper’s secondary author who contributed to each step of the project, was chosen to join the research team because of his expertise in system control theory. He says the project was a success because of ASU’s extensive robotics and machine learning resources.

“We had access to state-of-the-art computing facilities, and we were able to collaborate with world-class researchers in the robotics and machine learning fields,” Moradi says. “ASU also has a strong focus on interdisciplinary research, which was essential for this project, as it required expertise in both fields.”

Transforming the future with robotics and machine learning

The research team plans to take full advantage of ASU’s machine learning and robotics expertise, along with what they’ve learned from this project, to further develop trajectory control capabilities for robots. Zhai says the researchers plan to tackle the challenge of applying their findings to controlling robots in three-dimensional space, which would enable a robot such as an autonomous drone to move vertically and horizontally.

The researchers are also investigating the integration of model predictive control, a method of system control in which a mathematical function seeks to use minimal resource costs to produce a desired outcome in the use of machine learning in robotics. Zhai notes model predictive control is useful for its ability to operate systems with multiple variables while considering operational constraints.

“Integrating model predictive control with machine learning for a dynamical system is an exciting fusion of classical control theory and modern computational techniques,” he says.

Moradi is also excited about the future robotics control possibilities.

“Machine learning can be used to develop controllers that are more robust, adaptable and efficient than traditional controllers,” he says. “I believe machine learning control will play a major role in the development of next-generation robotic systems.”

TJ Triolo

Communications Specialist, Ira A. Fulton Schools of Engineering

480-965-1314

ASU film school welcomes new screenwriting professor


October 12, 2023

For novelist and screenwriter Brian McAuley, storytelling isn’t just a profession; it’s one of the building blocks of humanity, a way to interact with and make sense of the world.

I can’t think of a more primal human activity than storytelling,” McAuley said. “It’s how we connect as a species, how we make sense of life. If you can master the fundamentals of screenwriting, you’ll have a foundational narrative skill set that will serve you not only in your filmmaking journey, but in every walk of life.” Portrait of ASU Clinical Assistant Professor Brian McAuley. ASU Clinical Assistant Professor Brian McAuley Download Full Image

McAuley brings his passion and expertise for good storytelling to The Sidney Poitier New American Film School at Arizona State University this fall as a new clinical assistant professor in screenwriting. McAuley previously taught at Columbia University, where he earned his MFA in film with a concentration in screenwriting, as well as Loyola Marymount University and Mount Saint Mary’s University.

McAuley is a versatile writer of various genres and has worked on projects as diverse as the Netflix family sitcom “Fuller House” and the Lifetime Network thriller “Nanny Cam.” He’s written feature horror films, including 2017’s “Dismissed,” starring Dylan Sprouse, and is the author of the grisly fun 2022 horror novel “Curse of the Reaper,” which pays satirical homage to beloved 1980s slasher flicks, and the forthcoming Christmastime slasher novella “Candy Cain Kills,” which hits shelves Nov. 14.

Question: What attracted you to teach at The Sidney Poitier New American Film School?

Answer: I’m a firm believer that educational institutions should be actively invested in community building, so I was immediately attracted to the collaborative spirit I sensed at The Sidney Poitier New American Film School. After meeting with some of the brilliant faculty and passionate students, I knew I’d found my new creative home. When I first visited the MIX Center, I was blown away by the Hollywood studio-level facilities available to filmmaking students. It’s not just an immersive training ground for industry innovation, but also a neighborhood hub that encourages civic engagement with the city of Mesa.

Q: What does Sidney Poitier’s legacy mean to you, and how is it relevant to current-day film students?

A: My first encounter with Poitier was through his outstanding performance in “In the Heat of the Night.” Given the powerful message of that film, it was no surprise to discover that Poitier was instrumental in paving the way for diversity and representation in Hollywood. This is an issue that I’ve been engaged with through my collaborative work with the Center for Scholars and Storytellers. I’ve written articles and co-authored research reports with social scientists investigating the positive impact that authentic representation can have on youth development. It’s so important for current-day students to understand Poitier’s legacy because there’s still so much work left to be done, and it’s up to the next generation of filmmakers to pave the way toward an even more diverse and inclusive future.

Q: You’ve written both screenplays and novels. How do you approach storytelling in different mediums and genres?

A: No matter what medium or genre I’m writing in, character is everything. A clever concept is all well and good, but if I can’t get you to care about the people in the story I’m telling, your emotional investment will inevitably wane. Once I’ve locked into a character who feels like an authentic human being, I can start constructing a plot that will challenge them to change and grow. Through my diverse professional writing experience, I’ve accrued a toolbox full of techniques that work to varying degrees in different mediums and genres. The fun of the process comes from exploring and experimenting with them in different creative sandboxes.

Q: What do you want students to know about you and your teaching style?

A: Whether I’m teaching a lecture, workshop or film studies course, my goal is to help you discover the story you’re most passionate about telling. By exposing you to a diversity of voices in world cinema and providing exercises to flex your storytelling muscles, you’ll discover your own voice along with that inner spark that keeps you coming back to the keyboard. I’ll give you the evergreen tools you need to bring your vision to life, along with the professional perspective to help prepare you for an ever-evolving industry.

Q: Who are your biggest screenwriting influences?

A: I grew up on a steady stream of classic horror cinema, so my early influences include the work of John Carpenter and Sam Raimi. I also love Billy Wilder for his ability to blend pathos into his comedies and melodramas, and Paddy Chayefsky for his sharp social satires. In the modern landscape, I find constant inspiration in the work of Jordan Peele and Guillermo del Toro, two storytelling titans who have helped the horror genre gain more of the critical recognition it deserves.

Q: You’ve written in many genres, but you’re most prolific in horror. What draws you to the horror genre? Do you think it’s misunderstood?

A: I think it’s very easy for people to dismiss the horror genre as somehow less-than. Ironically, that’s exactly what the genre is about: the capital-O “Other” retaking the spotlight. As film theorist Robin Wood said, the true subject of the horror genre is the struggle for recognition of all that our civilization represses or oppresses. For that reason, the horror genre is home to some of the most progressive and inclusive communities I’ve ever encountered. It’s a genre of catharsis that challenges us to push beyond our comfort zones, to dabble in the danse macabre and make friends with memento mori, and I believe there’s life-affirming value in that. It’s also just a bloody good time!

Q: What can you tell us about your new book, “Candy Cain Kills,” out Nov. 14?

A:Candy Cain Kills” is the second entry in Shortwave Publishing’s "Killer VHS Series," which one reviewer dubbed “the modern day Goosebumps for adults.” These are standalone novellas that harken back to the VHS rental days with 1980s aesthetics and campy vibes. My story is about a struggling family who rents a cottage in the snowy wilderness over Christmas in the hopes of mending broken bonds. Unfortunately, their getaway was the site of a grisly crime 10 years ago … and the legendary Candy Cain is back with a vengeance. It’s a gory thrill ride that pays homage to holiday slasher flicks like “Black Christmas” and “Halloween,” but I’m especially proud that early reviewers are highlighting the strong character development with LGBTQ+ and disability representation.

Q: We have to ask: What is your favorite horror film and why?

A: How dare you make me choose! Honestly, it changes all the time, but there’s no denying that “Scream” shaped me in ways that few other films have. I was a child of the WB who religiously watched “Buffy the Vampire Slayer” and “Dawson’s Creek.” With “Scream,” screenwriter Kevin Williamson effortlessly melded a teen comedy with a slasher mystery. It opened the door for me to discover a whole back catalog of scary movies I didn’t even know existed. Once I crossed that threshold, there was no turning back for me.

For more stories on The Sidney Poitier New American Film School, visit film.asu.edu/news.

Communications Program Coordinator, The Sidney Poitier New American Film School