12:00 pm to 1:30 pm
3305 Newell-Simon Hall
Abstract:
Safe autonomy in the real world requires more than safety in structured, low-dimensional settings. Robots deployed in everyday environments must cope with non-stationarity—objectives and dynamics that change due to human preferences or evolving operating conditions—and must also scale safety reasoning to high-dimensional robots and environments, where perception, dynamics, and safety constraints can be complex and tightly coupled.
This thesis presents safety methods that are both adaptive and scalable. We start with an approach for adapting to varying control objectives by incorporating short context demonstrations, enabling rapid objective inference and controller adjustment in a physical human–robot collaboration task. Next, we present a method for adapting safety to parameter-varying dynamics with formal guarantees, leveraging the structure of provably safe controller synthesis to update safety certificates in real time to preserve feasibility.
We then shift to safety challenges that emerge in high-dimensional systems. For safety analysis at scale, we propose λ-Reachability, a method for learning safety value functions that interpolates between local self-consistency and long-horizon safety targets, improving both feasible-boundary classification and safety-margin estimation in high-dimensional humanoid settings. Finally, to handle the fact that learned safety representations can be imperfect in practice, we present the Projected Safe Set Algorithm (p-SSA), a feasibility-aware safe control method that mitigates infeasible constraint sets arising from dense, multi-body collision constraints in dexterous humanoid operation, achieving robust collision avoidance in simulation and on real hardware.
By unifying adaptive control, scalable safety analysis, and feasibility-aware approaches, this thesis takes a step toward robots that can operate safely amid the uncertainty, complexity, and interactivity of the real world.
Thesis Committee Members:
Professor Changliu Liu (chair)
Professor Zac Manchester
Professor Guanya Shi
Professor Chuchu Fan (MIT)
Link to draft thesis document: https://www.dropbox.