Hongzhan Yu
YOU?
Author Swipe
View article: Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis
Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis Open
Time-optimal trajectories drive quadrotors to their dynamic limits, but computing such trajectories involves solving non-convex problems via iterative nonlinear optimization, making them prohibitively costly for real-time applications. In …
View article: Safe Human Robot Navigation in Warehouse Scenario
Safe Human Robot Navigation in Warehouse Scenario Open
The integration of autonomous mobile robots (AMRs) in industrial environments, particularly warehouses, has revolutionized logistics and operational efficiency. However, ensuring the safety of human workers in dynamic, shared spaces remain…
View article: Controllable Motion Generation via Diffusion Modal Coupling
Controllable Motion Generation via Diffusion Modal Coupling Open
Diffusion models have recently gained significant attention in robotics due to their ability to generate multi-modal distributions of system states and behaviors. However, a key challenge remains: ensuring precise control over the generate…
View article: Activation-Descent Regularization for Input Optimization of ReLU Networks
Activation-Descent Regularization for Input Optimization of ReLU Networks Open
We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We analyze local optimization steps in both the input space and the space of activation patt…
View article: Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance
Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance Open
There are two major challenges for scaling up robot navigation around dynamic obstacles: the complex interaction dynamics of the obstacles can be hard to model analytically, and the complexity of planning and control grows exponentially in…
View article: Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation
Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation Open
Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the opti…