Anca Dragan Publishes “Expressing Robot Incapability”
Anca Dragan and Sandy Huang, along with an additional researcher from Cornell, presented this paper at the 2018 ACM/IEEE International Conference on Human-Robot Interaction in Chicago, IL. The abstract reads:
Meet the Woman Teaching AI About Human Values
Anca Dragan was featured in a an article on Forbes where she talked about her research in AI and robotics, including value alignment, inferring human values, and second-guessing humans. You can read more here.
Anca Dragan Publishes “Learning from Richer Human Guidance – Augmenting Comparison-Based Learning with Feature Queries”
Anca Dragan, along with two researchers from UC Merced, published this article in arXiv. The abstract reads:
Stuart Russell – “Autonomous Weapons The New Weapons of Mass Destruction?”
CHAI’s PI Stuart Russell published “Autonomous Weapons: The New Weapons of Mass Destruction?” in The Security Times. In the piece, he discusses the implications and safety concerns of autonomous weapons, comparing them to weapons of mass destruction due to their scalability, cost-effectiveness, and ability to become fully autonomous. The article can be found here.
Joseph Halpern Publishes “Information Acquisition Under Resource Limitations in a Noisy Environment”
CHAI’s Joseph Halpern and his colleague Matvey Soloviev at Cornell University published this paper in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2018. The abstract reads:
Juliana Schroeder Publishes “Trusting in Machines – How Mode of Interaction Affects Willingness to Share Personal Information with Machines”
CHAI affiliate Juliana Schroeder along with Matthew Schroeder presented this paper at the Hawaii International Conference on System Sciences, Big Island, HI. We would like to congratulate her on the paper being nominated for the best paper award! The abstract reads:
CHAI and OpenAI Work Together on Inverse Reward Design
CHAI PI Stuart Russell and co-PI Anca Dragan, with a number of other authors from Berkeley’s School of Electrical Engineering and Computer Science and one from OpenAI, published “Inverse Reward Design” in the 31st Conference on Neural Information Processing Systems held in Long Beach, California back in last December. The abstract reads:
Anca Dragan Publishes “Learning Robot Objectives from Physical Human Interaction”
CHAI co-PI Professor Anca Dragan published “Learning Robot Objectives from Physical Human Interaction” with researchers from UC Berkeley’s EECS and Rice University in 1st Conference on Robot Learning in November 201. The paper’s abstract reads:
Stuart Russell Works with Future of Life Institute, Publishes Critically Acclaimed Short-Film ‘Slaughterbots’
CHAI’s principle investigator Stuart Russell in conjunction with the Future of Life Institute released Slaughterbots, a short-film highlighting the dangers of armed micro-drones with swarm intelligence being used for targeted assassinations and terrorist attacks. The film created a vast amount of media coverage, with major newspapers such as The Guardian covering it and generated discussions at major think-tanks such as the Center for New American Security. More can be read about it here.