Coexistence of chaos and stability. These visualizations of the system’s output show broad patterns of instability, but localized patterns of stability.
Credit: Inoue et al.
Autonomous functions for robots, such as spontaneity, are highly sought after.
Many control mechanisms for autonomous robots are inspired by the functions of animals, including humans. Roboticists often design robot behaviors using predefined modules and control methodologies, which makes them task-specific, limiting their flexibility. Researchers offer an alternative machine learning-based method for designing spontaneous behaviors by capitalizing on complex temporal patterns, like neural activities of animal brains. They hope to see their design implemented in robotic platforms to improve their autonomous capabilities.
Robots and their control software can be classified as a dynamical system, a mathematical model that describes the ever-changing internal states of something. There is a class of dynamical system called high-dimensional chaos, which has attracted many researchers as it is a powerful way to model animal brains. However, it is generally hard to gain control over high-dimensional chaos owing to the complexity of the system parameters and its sensitivity to varying initial conditions, a phenomenon popularized by the term “butterfly effect.” Researchers from the Intelligent Systems and Informatics Laboratory and the Next Generation Artificial Intelligence Research Center at the University of Tokyo explore novel ways for exploiting the dynamics of high-dimensional chaos to implement humanlike cognitive functions.
“There is an aspect of high-dimensional chaos called chaotic itinerancy (CI) which can explain brain activity during memory recall and association,” said doctoral student Katsuma Inoue. “In robotics, CI has been a key tool for implementing spontaneous behavioral patterns. In this study, we propose a recipe for implementing CI in a simple and systematic fashion only using complicated time-series patterns generated by high-dimensional chaos. We felt our approach holds potential for more robust and versatile applications when it comes to designing cognitive architectures. It allows us to design spontaneous behaviors without any predefined explicit structures in the controller, which would otherwise serve as a hindrance.”
Reservoir computing (RC) is a machine learning technique that builds on dynamical systems theory and provides the basis of the team’s approach. RC is used to control a type of neural network called a recurrent neural network (RNN). Unlike other machine learning approaches that tune all neural connections within a neural network, RC only tweaks some parameters while keeping all other connections of an RNN fixed, which makes it possible to train the system faster. When the researchers applied principles of RC to a chaotic RNN, it exhibited the kind of spontaneous behavioral patterns they were hoping for. For some time, this has proven a challenging task in the field of robotics and artificial intelligence. Furthermore, the training for the network takes place prior to execution and in a short amount of time.
“Animal brains yield high-dimensional chaos in their activities, but how and why they utilize chaos remains unexplained. Our proposed model could offer insight into how chaos contributes to information processing in our brains,” said Associate Professor Kohei Nakajima. “Also, our recipe would have a broader impact outside the field of neuroscience since it can potentially be applied to other chaotic systems too. For example, next-generation neuromorphic devices inspired by biological neurons potentially exhibit high-dimensional chaos and would be excellent candidates for implementing our recipe. I hope we will see artificial implementations of brain functions before too long.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Driving Toward Interoperability for Warehouse Robotson July 6, 2021 at 1:53 pm
Can different warehouse robots play nice together? Members of a standards group explain how it's happening in this MCM CommerceChat podcast.
- ‘Robots Don’t Need Lunch Breaks’: Grubhub Rolls Out Food-Delivering Robotson July 6, 2021 at 1:40 pm
Food delivery service Grubhub announced Tuesday its plans to use robots to deliver food on college campuses this fall. The company partnered with Russian technology firm Yandex to use its “rover” ...
- University of Buffalo’s Souma Chowdhury Receives NSF CAREER Award to Design Teams of Autonomous Robotson July 6, 2021 at 12:00 pm
The University of Buffalo recently announced that six of its researchers, including Indian American Souma Chowdhury, have received early career award grants from the National Science Foundation or the ...
- Yandex Self-Driving Group and Grubhub Partner for Robot Delivery on ...on July 6, 2021 at 8:47 am
Yandex autonomous delivery robots will expand Grubhub's delivery capabilities, including in campus areas only accessible by foot MOSCOW and AMSTERDAM, NETHERLANDS / ACCESSWIRE / July 6, 2021 / Yandex ...
- Reply Shapes the Future of Autonomous Mobile Robots with the Power of Microsoft Azureon July 6, 2021 at 4:30 am
Reply announced today that it has developed an end-to-end solution architecture for autonomous mobile robots (AMR) on Microsoft Azure that enables new ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Spontaneous robotic behaviors
- The Role of Emotional Intelligence in HealthCare: Bridging the Gaps of Communicationon June 29, 2021 at 7:49 am
spontaneous emotional learners. Increased awareness of the emotional triggers that set us up to fail to communicate effectively with our patients and co-workers may prevent unwanted behaviors and ...
- Why Robopets Will Never Be Real Enoughon June 28, 2021 at 11:07 pm
“The same principle applies if you wanted to use these robots in a home environment; that robot just needs to be trained to have different behaviors ... to the sort of spontaneous yet familiar ...
- Is Machine Learning The Key To Unlocking Gen Z Engagement? A Discussion With Jonathan Jadali Of Ascendon June 23, 2021 at 5:00 pm
robotic. Gen Z will be an important moment for machine learning marketing as it will help us get closer to contextual AI - machines that more accurately predict and reflect human behavior.
- Yoga Sutra 19 Moment To Momenton June 20, 2021 at 9:38 am
It is spontaneous. If Buddha feels hungry ... They have become so unfeeling, so mechanical, robot-like. Death is a great phenomenon. When you can feel hunger, why can’t you feel death?
- Blavatnik National Awards for Young Scientists announces the finalists of 2021on June 15, 2021 at 5:04 am
She discovered a neural pathway that underlies an animal's willingness to engage in compulsive, reward-seeking behaviors despite ... modern computer vision with robotics. Asegun Henry ...