Showing first, co-first*, or corresponding† author papers only. Full list on Google Scholar →
We present MARS, a generative policy that adaptively invokes stochasticity only when behavioral branching truly matters and reverts to deterministic learning otherwise, yielding 16.67% higher success and 83.20% lower inference latency in real-world tests.
APEX is a plug-and-play framework that bridges the execution gap of learned manipulation policies by reconstructing dynamically feasible references from policy outputs and adapting them online via state feedback.
We close the prediction–observation loop in world models with a lightweight feedback state that corrects future predictions online, paired with action-aware guidance to emphasize controllable dimensions, reducing prediction error by up to 76.4% and improving OOD success by 30%.
We present FLASH, an efficient visuomotor policy that replaces iterative denoising with continuous Legendre polynomial trajectories, enabling single-step inference for real-time robot control.
The presented trajectory optimizer outputs trajectories that are friendly to the following control level.
We present ADAPT, an analytical disturbance-aware framework for humanoid locomotion that infers joint-level external disturbances from robot dynamics and proprioception alone, without specialized sensors, and feeds them back into policy training for robustness to pushes, payloads, and impacts.
We propose PhyFilter, which enhances both generalization and interpretability of robot learning. PhyFilter operates by correcting learning outcomes according to readily accessible physical differential structure and real-time state feedback.
A comprehensive survey of world models for robot learning, covering world models as policies and as simulators across recent literature.
We introduces A2A, an efficient generative paradigm that replaces noise-based initialization with action-to-action transport.
We present a learning-based observer, enabling accurate prediction of the coupled disturbance consisting of internal uncertainties and external disturbances.
We present two converged uncertainty prediction frameworks, enabling accurate prediction of two general kinds of uncertainties, respectively.
We present feedback neural networks, showing that a feedback loop can flexibly correct the learned latent dynamics of neural ordinary differential equations (neural ODEs), leading to a prominent generalization improvement.
We present a framework, namely EVOLVER, to mimic the bio-behavior for robotics to achieve rapid transient reaction ability and high precision steady-state performance simultaneously.
Different from standard approaches that achieve precise tracking by feedforward compensating the estimated drag, this work presents a scheme to appropriately utilize drag.
A scheme of anti-disturbance agile flight control is developed for a maneuverable quadrotor unmanned aerial vehicle, subject to the aerodynamic drag, dynamic shift of center of gravity, and motor dynamics.
A safety control strategy based on a novel nonlinear disturbance observer and geometric control is developed for a quadrotor unmanned aerial vehicle, subject to the disturbances caused by center-of-gravity shift and loss of motor efficiency.
This paper presents a multiple observers-based anti-disturbance control scheme against multiple disturbances for a quadrotor unmanned aerial vehicle.
This paper presents an embedded micro loop to enhance the anti-disturbance performance for unmanned aerial vehicles.