Aude Billard facts for kids

Quick facts for kids Aude Gemma Billard
Portrait of Aude Billard
Born	1971 (age 53–54) Lausanne, Switzerland
Nationality	Swiss
Alma mater	B.S. and M.S. École Polytechnique Fédérale de Lausanne (EPFL), M.S. and Ph.D. University of Edinburgh
Known for	Applying machine learning to robotics to improve learning and task performance
Awards	2016 Nominated as Member of SATW, Swiss Academy of Engineering Sciences, 2016 Nominated for Outstanding Women in Academics SNSF, 2015 King-Sun Fu Best Transactions Paper Award, IEEE & Robotics and Automation Society, 2003 The Outstanding Young Person in Science and Innovation, Junior Chamber of Commerce, 2002 SNF Professeur Boursier, Career Award from Swiss National Science Foundation, 2001 Innovative Teaching Grant - Intel Corporation, 1999 Fellowship Medicus Foundation, 1996-97 Scholarship, Swiss National Science Foundation
Scientific career
Fields	Machine learning, robotics, physics
Institutions	École Polytechnique Fédérale de Lausanne (EPFL)

Aude G. Billard, born in 1971, is a Swiss scientist. She works with robotics and machine learning. Machine learning is how computers learn from data without being directly programmed.

Professor Billard teaches at the Swiss Federal Institute of Technology in Lausanne (EPFL). Her research helps robots learn from humans. She focuses on how robots and humans can work together. Her work has been praised by the Institute of Electrical and Electronics Engineers (IEEE). She helps lead the IEEE Robotics and Automation Society (RAS).

Early Life and Education

Aude Billard was born in Lausanne, Switzerland, on August 6, 1971. She studied physics at the Swiss Federal Institute of Technology at Lausanne (EPFL). She earned her Bachelor's degree in 1994 and her Master's degree in 1995. During this time, she studied Particle Physics and worked at CERN, a famous research center.

After EPFL, Billard went to the University of Edinburgh in Scotland. There, she studied Artificial Intelligence. She earned another Master's degree in 1996. Then, she completed her PhD in Artificial Intelligence in 1998.

After her PhD, Billard returned to Switzerland. She did more research at EPFL and the Swiss Artificial Intelligence Lab until 1999.

How Robots Learn by Copying

During her studies, Billard worked on making robots learn by copying. She wanted to build systems that could communicate. She created a system where robots could learn simple language. She used two robots, one acting as a teacher and one as a student.

Her goal was to make the learning simple and useful for many robots. She showed that robots could learn by imitation. They used simple math and light sensors to understand movements. Billard also thought that robots could learn even better with more complex thinking. This would help them connect actions with results.

DRAMA: A Robot Learning Model

Billard developed a special model for robots to learn, called DRAMA. This stands for Dynamical – Recurrent – Associative – Memory – Architecture. DRAMA helps robots learn by imitation. It makes sure a robot's actions consider its past interactions. It also looks at the robot's own internal thoughts.

She used DRAMA to teach robots many things. For example, a human or another robot could teach a student robot. They could teach it to understand the world, learn a simple language, or copy movements.

After her PhD, Billard also studied how multiple robots could communicate. She created a model that could predict how well robots would share information. This helped them learn tasks together.

Career and Research

In 1999, Billard started working at the University of Southern California in the computer science department. She became a professor at EPFL in 2002. She was promoted several times, becoming a full professor in 2013.

Her research focuses on using machine learning to control robots. These robots are designed to interact with humans. Her lab at EPFL is called the Learning Algorithms and Systems Laboratory (LASA). It started in 2006. This lab is known for teaching robots to do tasks with human-like skill.

The LASA lab explores several key areas:

• How humans and robots interact.
• Using machine learning for robots.
• Making robots adapt quickly.
• Helping robots grasp and move objects skillfully.
• Understanding how the brain works to build better robots.

All their work aims to create robots that can adapt, interact with humans, and learn from experience.

Billard is also very active in the science community. She holds leadership roles in many groups. She is the president of the EPFL Teaching Body Assembly. She is also a senior editor for a top robotics journal. She helps lead the IEEE Robotics and Automation Society.

Making Robots Better at Imitation

In 2001, Billard created a model for robots to imitate humans. This model could learn how an arm moves when throwing or catching. It could also learn from different examples and adapt quickly.

She continued to use brain-inspired models to train robots. These models helped robots learn complex arm movements by copying. Her models could imitate a teacher as well as a human could. Billard also explored how to make robot brains more flexible, like human brains. She added concepts like homeostatic plasticity and Hebbian reinforcement learning to her robot models.

In 2006, Billard added social cues to robot interactions. This helped robots switch between learning and doing tasks. She used gesture recognition and motion sensors. This made robots behave more naturally when learning socially.

Teaching Robots Complex Skills

Billard's work has greatly improved how robots learn precise movements. Since 2008, she has shown how robots can learn fine movements and use them in different situations.

Her team used golf putting as an example. They taught a robot to putt. The robot learned from its mistakes, just like a human. It got better by understanding successful and failed putts. Soon after, they taught robots to catch objects in the air. A video of their robot catching objects became very popular online.

In 2015, Billard's team used EMG recordings. These recordings measure muscle activity. They used them to understand human hand movements early on. This helped them coordinate a robot hand with human arm movements. They could predict three common grasps with 90% accuracy.

In 2016, Billard and her students won awards for their work. They showed how multiple robot arms could work together. Their system could adapt and coordinate arms to catch fast-moving objects.

Her team also taught robots to learn complex tasks step-by-step. In 2016, they showed how robots could learn both small movements and the order of tasks. In 2017, they improved this by combining different learning methods. This allowed robots to learn from human demonstrations.

Robots Adapting to Human Touch

In 2018, Billard and her team developed a way for robots to change tasks. They could do this based on how humans physically interacted with them. Robots learned to adjust their movements when a human interfered. This was tested in real-world situations.

Awards and Honors

• (2017) European Research Council Advanced Grant for Skill Acquisition in Humans and Robots
• (2016) Nominated as Member of SATW, Swiss Academy of Engineering Sciences
• (2016) Nominated for Outstanding Women in Academics, SNSF, AcademiaNet
• (2016) Best Student Paper Award, RSS
• (2015) King-Sun Fu Best Transactions Paper Award, IEEE & Robotics and Automation Society
• (2013) Best reviewer award for the IEEE Robotics and Automation Society
• (2012) Best Cognitive Robotics Paper Award, Int. Conf. on Robotics and Automation (ICRA)
• (2011) JTSC Novel Technology Best Paper Award, IEEE Int. Conf. Intelligent & Robotics Systems (IROS)
• (2011) Nominated for Best Paper Award, Neural Information Processing Symposium
• (2007) Nominated for Best Paper Award, IEEE Int. Conf. on Humanoid Robots
• (2004) Best Paper Award, Workshop on Universal Access and Assistive Technology (CWUATT)
• (2003) The Outstanding Young Person in Science and Innovation, Junior Chamber of Commerce, Switzerland
• (2002) SNF Professeur Boursier, Career Award from Swiss National Science Foundation
• (2001) Innovative Teaching Grant, Intel Corporation
• (1999) Fellowship, Medicus Foundation, New York, USA
• (1996–97) Scholarship, Swiss National Science Foundation, Switzerland

Selected Publications

• Aude Gemma Billard. 2016. Towards Reproducing Humans? Exquisite Dexterity and Reactivity. In The Eleventh ACM/IEEE International Conference on Human Robot Interaction (HRI ’16). IEEE Press, 99.
• Nadia Figueroa, Ana Lucia Pais Ureche, and Aude Billard. 2016. Learning Complex Sequential Tasks from Demonstration: A Pizza Dough Rolling Case Study. In The Eleventh ACM/IEEE International Conference on Human Robot Interaction (HRI ’16). IEEE Press, 611–612.
• Ana-Lucia Pais Ureche and Aude Billard. 2015. Learning Bimanual Coordinated Tasks From Human Demonstrations. In Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts (HRI’15 Extended Abstracts). Association for Computing Machinery, New York, NY, USA, 141–142. DOI:https://doi.org/10.1145/2701973.2702007
• Iason Batzianoulis, Sahar El-Khoury, Silvestro Micera, and Aude Billard. 2015. EMG-Based Analysis of the Upper Limb Motion. In Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts (HRI’15 Extended Abstracts). Association for Computing Machinery, New York, NY, USA, 49–50. DOI:https://doi.org/10.1145/2701973.2701997
• Daniel H. Grollman and Aude G. Billard. 2011. Learning from failure: extended abstract. In Proceedings of the 6th international conference on Human-robot interaction (HRI ’11). Association for Computing Machinery, New York, NY, USA, 145–146. DOI:https://doi.org/10.1145/1957656.1957703
• Eric Sauser, Brenna Argall, and Aude Billard. 2011. The life of icub, a little humanoid robot learning from humans through tactile sensing. In Proceedings of the 6th international conference on Human-robot interaction (HRI ’11). Association for Computing Machinery, New York, NY, USA, 393–394. DOI:https://doi.org/10.1145/1957656.1957798
• Elena Gribovskaya and Aude Billard. 2008. Combining dynamical systems control and programming by demonstration for teaching discrete bimanual coordination tasks to a humanoid robot. In Proceedings of the 3rd ACM/IEEE international conference on Human robot interaction (HRI ’08). Association for Computing Machinery, New York, NY, USA, 33–40. DOI:https://doi.org/10.1145/1349822.1349828
• Sylvain Calinon and Aude Billard. 2007. Incremental learning of gestures by imitation in a humanoid robot. In Proceedings of the ACM/IEEE international conference on Human-robot interaction (HRI ’07). Association for Computing Machinery, New York, NY, USA, 255–262. DOI:https://doi.org/10.1145/1228716.1228751
• Sylvain Calinon and Aude Billard. 2005. Recognition and reproduction of gestures using a probabilistic framework combining PCA, ICA and HMM. In Proceedings of the 22nd international conference on Machine learning (ICML ’05). Association for Computing Machinery, New York, NY, USA, 105–112. DOI:https://doi.org/10.1145/1102351.1102365
• Aude Billard and Maja J. Matarić. 2000. A biologically inspired robotic model for learning by imitation. In Proceedings of the fourth international conference on Autonomous agents (AGENTS ’00). Association for Computing Machinery, New York, NY, USA, 373–380. DOI:https://doi.org/10.1145/336595.337544
• Kerstin Dautenhahn and Aude Billard. 1999. Bringing up robots or—the psychology of socially intelligent robots: from theory to implementation. In Proceedings of the third annual conference on Autonomous Agents (AGENTS ’99). Association for Computing Machinery, New York, NY, USA, 366–367. DOI:https://doi.org/10.1145/301136.301237

Political Career

Aude Billard is a member of the Social Democratic Party of Switzerland. In 2022, she was elected to the Grand Council of Vaud. This is a local government body in Lausanne.

Personal Life

Billard is a mother to three daughters.