Blog
Revisiting Radar Camera Alignment by Contrastive Learning for 3D Object Detection
Recently, 3D object detection algorithms based on radar and camera fusion have shown excellent performance, setting the stage for their application in autonomous driving perception tasks. Existing methods have focused on dealing with feature misalignment caused by the domain gap between radar...
Fast Online Adaptive Neural MPC via Meta-Learning
Data-driven model predictive control (MPC) has demonstrated significant potential for improving robot control performance in the presence of model uncertainties. However, existing approaches often require extensive offline data collection and computationally intensive training, limiting their ability to adapt online. To address these...
SILM: A Subjective Intent Based Low-Latency Framework for Multiple Traffic Participants Joint Trajectory Prediction
Trajectory prediction is a fundamental technology for advanced autonomous driving systems and represents one of the most challenging problems in the field of cognitive intelligence. Accurately predicting the future trajectories of each traffic participant is a prerequisite for building high safety and...
PINN-MEP: Continuous Neural Representations for Minimum-Energy Path Discovery in Molecular Systems
Characterizing conformational transitions in physical systems remains a fundamental challenge in the computational sciences. Traditional sampling methods like molecular dynamics (MD) or MCMC often struggle with the high-dimensional nature of molecular systems and the high energy barriers of transitions between stable states....
Fully Scalable MPC Algorithms for Euclidean k-Center
The $k$-center problem is a fundamental optimization problem with numerous applications in machine learning, data analysis, data mining, and communication networks. The $k$-center problem has been extensively studied in the classical sequential setting for several decades, and more recently there have been...
Fast and Modular Whole-Body Lagrangian Dynamics of Legged Robots with Changing Morphology
Fast and modular modeling of multi-legged robots (MLRs) is essential for resilient control, particularly under significant morphological changes caused by mechanical damage. Conventional fixed-structure models, often developed with simplifying assumptions for nominal gaits, lack the flexibility to adapt to such scenarios. To...
Study of Auto-igniting Spray Flame in Vitiated Swirling Hot Coflow using flamelet generated model
Swirl-stabilized auto-igniting spray flames are essential for designing efficient and clean combustion systems. The present study performs large eddy simulations (LES) of the dilute auto-igniting methanol flame in a vitiated, hot coflow of varying swirl intensities. The six-dimensional Flamelet Generated Manifold (FGM)...
Measurement of the Temperature Dependence of the Refractive Index of CdZnTe
We have been developing a CdZnTe immersion grating for a compact high-dispersion mid-infrared spectrometer (wavelength range 10–18 $\mu$m, spectral resolution $R = \lambda/\Delta \lambda > 25,000$, operating temperature $T < 20$ K). Using an immersion grating, the spectrometer size can be reduced...
Probing Bulk Band Topology from Time Boundary Effect in Synthetic Dimension
An incident wave at a temporal interface, created by an abrupt change in system parameters, generates time-refracted and time-reflected waves. We find topological characteristics associated with the temporal interface that separates distinct spatial topologies and report a novel bulk-boundary correspondence for the...
An Explicit and Efficient $O(n^2)$-Time Algorithm for Sorting Sumsets
We present the first explicit comparison-based algorithm that sorts the sumset $X + Y = \{x_i + y_j,\ \forall 0 \le i, j < n\}$, where $X$ and $Y$ are sorted arrays of real numbers, in optimal $O(n^2)$ time and comparisons. While...