Abstract: Designers draw extensively to externalize their ideas and communicate with others. But drawings are currently not directly interpretable by computers. To test their ideas against physical reality, designers have to create 3D models suitable for simulation and 3D printing. However, the visceral and approximate nature of drawing clashes with the tediousness and rigidity of 3D modeling. As a result, designers only model finalized concepts, and have no feedback on feasibility during creative exploration.

Abstract: Human feedback is widely considered the 'gold standard' for AI alignment, but what if this 'gold' reflects inherently diverse and conflicting human views on what constitutes ‘good’ and ‘safe’? This keynote will explore the technical and ethical challenges posed by differing viewpoints and opinions across individuals and groups.

Title of the Talk: HAIR - Healthcare Applications and Interactive Robotics

Invited Speaker: Ildar Farkhatdinov

Time: June 2nd, Monday, between 15:00-16:00 

Location: Earl Mountbatten Building, Room EM2.44. 

Abstract:

Julia Whittle is a Senior Account Executive at Microsoft, specialising in managing accounts for government agencies. Julia has a passion for learning - having qualified as an electrical and electronic engineer and later being awarded an MBA. With a diverse career that began as an engineer on oil rigs, Julia has transitioned through various roles to her current position in sales. Her journey reflects a unique blend of technical expertise and business acumen. She describes herself as a techie with empathy! Julia is deeply passionate about accessibility.

Abstract: We present a framework to improve shared autonomy in teleoperated robotic systems for complex assembly tasks.

Abstract: In this talk, we cover four aspects of research on general manipulation for assistive robotics : i), efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios where gathering multi-task data involving humans requires strenuous effort; ii), effectively learning robot action trajectories with our flow matching policy; iii) sim-to-real physics learning for deformable manipulation and robot-assisted dressing;  iv) multi-modal (vision, tactile, audio) learning.

Title: Uncertainty-Aware Motion Planning for Autonomous Driving in Interactive Urban Scenarios

Speaker: Zhaocheng Liu

Title: Learning protein transition states from simulation data via Flow Matching

Abstract: We have a long history of robotics in manufacturing, and over the past 20 years a second wave of robotics in warehouses - both controlled environments. As we bring robots into the world to operate in unconstrained environments around the general public, new challenges arise. This talk will review work from Willow Garage with early humanoid robots, and some of the challenges of bringing robots to hotels and hospitals. We will introduce the Stanford Robotics Center, which is looking at the next generation of challenges.

Abstract: Fiber Bragg Gratings (FBGs) based shape sensing allows for precise, real-time tracking of medical instruments within the body. Standard FBG (SFBG) sensors detect shape changes by analysing the reflected light wavelengths from multiple FBGs along an optical fibre, which respond to strain variations as the fibre bends or twists. Tilted Fiber Bragg Gratings (TFBGs) offer the additional capability of sensing temperature and biologically relevant signals like pH independent of strain in situ.