When: Thursday, 9th of July, 1:00pm AEDT
Where: This seminar will be partially presented at the ACFR seminar area, J04 lvl 2 (Rose St Building) and partially online via Zoom. RSVP
Title: Manipulating Uncertainty: Towards Reliable In-the-wild Dexterity with Less Data
Speaker: Hrishikesh Sathyanarayan
Abstract:
Robotic manipulation is increasingly expected to achieve reliable operation in uncertain environments such as kitchens, warehouses, and homes, yet performance in these settings remains highly sensitive to latent physical uncertainties that are often difficult to know in advance.
This challenge is especially prominent in contact-rich tasks, where uncertainty in friction, mass, geometry, inertia, or compliance can amplify large differences in how objects move, slip, stick, or deform during interaction. Modern robot learning has made significant progress by using large-scale data to reduce and adapt to uncertainty during training, but such methods often require far more data than necessary when they cannot deliberately target contact interactions that reveal the physical uncertainties that are most crucial for reliable manipulation performance. In this talk, I argue that the central challenge in manipulation is not merely the presence of physical uncertainty, but rather the lack of principled methods for deciding which uncertainties must be reduced, represented, or accounted for to achieve reliable dexterity. My work asks whether robots can become more deliberate about uncertainty by learning what is worth knowing, what can be ignored for the task at hand, and what must be accounted for during control. I will present data-efficient methods for uncertainty-aware manipulation learning and control, showing how robots can actively exploit contact dynamics to achieve strong learning performance from only a small number of informative interactions. Finally, I will discuss how explicit reasoning over task-relevant physical uncertainty enables robots to solve manipulation tasks reliably without requiring a fully precise model of the world.
Bio:
Hrishikesh Sathyanarayan is a PhD candidate in Mechanical Engineering at Yale University, and a member of the Computational Methods for Curious Robotics Lab, advised by Professor Ian Abraham. His research interests include contact-rich manipulation, data-efficient robot learning, and optimal control. Prior to Yale, Hrishi completed his Bachelor’s degree in Aerospace Engineering at Rutgers University.
Title: Generalizing Ergodic Coverage for Real-World Robotics
Speaker: Christian Hughes
Abstract:
As robotic exploration extends into new domains, robots are entrusted with missions under increasingly strict time and energy constraints, where success depends on prioritizing search according to each region’s importance. However, in settings like search-and-rescue, where success is critical, prioritized exploration must come with a formal guarantee that no region is left unexplored. Ergodic exploration offers a solution to this problem by guaranteeing full coverage with time spent in proportion to each region’s value, but existing methods are limited to static, well-defined domains. In this talk, I show how to extend these guarantees to domains of arbitrary geometry, at any scale, over unbounded time-horizons, and in environments that evolve as the robot explores, so that provable, importance-aware coverage becomes practical in the missions where it matters most.
Bio:
Christian Hughes is a PhD student in Mechanical Engineering at Yale University in the Computational methods for Curious Robots Lab (CoCuRo Lab). Before joining the CoCoRo Lab, he earned his B.S. and M.S. in Aerospace Engineering from Embry-Riddle Aeronautical University, with concentrations in astronautics and in dynamics and control systems. Christian’s research designs structured formulations of optimization problems that come with provable guarantees on the solution, with much of his recent work focused on exploration and coverage. His research is motivated by the belief that trustworthy robots must offer guarantees, because a system that usually works is not enough when mission success is critical. Christian’s recent work focuses on extending these guarantees to complex, real-world domains where robots actually operate.