31 accepted papers
Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consistent nature of kinematics across diverse domains, we aim to incorporate domain-…
Research in Machine Learning (ML) and AI evolves rapidly. Information Extraction (IE) from scientific publications enables to identify information about research concepts and resources on a large scale and therefore is a pathway to improve understanding and reproducibility of ML-related research. To
3D semantic occupancy prediction is essential for achieving safe, reliable autonomous driving and robotic navigation. Compared to camera-only perception systems, multi-modal pipelines, especially LiDAR-camera fusion methods, can produce more accurate and fine-grained predictions. Although voxel-base…
The choice of training objective is central to diffusion-based generative modeling in terms of both sample quality and distribution coverage. While standard maximum likelihood training provides a principled objective with strong theoretical grounding, empirical studies indicate that previous trainin…
Bipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile platforms, such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has inste
Bipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile plarforms such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has instea…
Trajectory world models play a crucial role in robotic dynamics learning, planning, and control. While recent works have explored trajectory world models for diverse robotic systems, they struggle to scale to a large number of distinct system dynamics and overlook domain knowledge of physical struct…
As spectrum congestion intensifies in wireless communication, efficient spectrum utilization through advanced sensing techniques has become increasingly important. This paper proposes a joint carrier frequency and two-dimensional (2-D) Direction of Arrival (DOA) estimation algorithm with signal reco…
Generative models that maximize model likelihood have gained traction in many practical settings. Among them, perturbation-based approaches underpin many state-of-the-art likelihood estimation models, yet they often face slow convergence and limited theoretical understanding. In this paper, we deriv…
We present a Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN) for learning-based contact perception. The architecture and connectivity of the MI-HGNN are constructed from the robot morphology, in which nodes and edges are robot joints and links, respectively. By incorporating the mor
The task of the multi-agent pathfinding (MAPF) problem is to navigate a team of agents from their start point to the goal points. However, this setup is unsuitable in the assembly line scenario, which is periodic with a long working hour. To address this issue, the study formalizes the streaming MAP
This paper presents a comprehensive analysis of two-channel modulo analog-to-digital converters (ADCs) systems, focusing on the sensitivity of ADC thresholds. By exploiting analytic number theory, we first investigate the relationship among ADC threshold precision, maximum signal dynamic range, and…
Unmanned aerial vehicle (UAV) communication plays a pivotal role in achieving ubiquitous connectivity for the sixth-generation (6G) networks. Accurate and real-time direction of arrival (DOA) estimation is crucial for beamforming in UAV communication systems. However, the existing high-precision DOA…
This paper addresses key challenges caused by high sampling rates in wideband joint spectrum sensing applications. A joint Direction of Arrival (DOA) and frequency estimation algorithm is proposed by utilizing the Cross-Covariance Matrix (CCM) constructed from the outputs of an efficient undersampli…
In the context of perceiving spatial information, researchers extensively investigate the use of large-scale arrays due to their numerous advantages such as high precision and resolution, as well as increased degrees of freedom. However, large-scale arrays may be impractical in certain applications…
Image-to-image (I2I) translation is vital in computer vision tasks like style transfer and domain adaptation. While recent advances in GAN have enabled high-quality sample generation, real-world challenges such as noise and distortion remain significant obstacles. Although Gaussian noise injection d…
This paper presents a theoretical analysis of multi-channel modulo analog-to-digital converters (ADCs) for high-dynamic range sampling under bounded noise. In particular, we derive the maximum error tolerance in terms of ADC dynamic range, signal dynamic range, and channel number. Additionally, we p…
This paper explores noise-mismatched models using the Hellinger distance. In many applications, the design/training stage often assumes an independent and identically distributed (i.i.d.) Gaussian prior noise, but the real world introduces Gaussian noise with arbitrary covariance, creating a mismatc…
Named Entity Recognition (NER) models play a crucial role in various NLP tasks, including information extraction (IE) and text understanding. In academic writing, references to machine learning models and datasets are fundamental components of various computer science publications and necessitate ac…
We present a new method to adapt an RGB-trained water segmentation network to target-domain aerial thermal imagery using online self-supervision by leveraging texture and motion cues as supervisory signals. This new thermal capability enables current autonomous aerial robots operating in near-shore…
This work presents a new method for unsupervised thermal image classification and semantic segmentation by transferring knowledge from the RGB domain using a multi-domain attention network. Our method does not require any thermal annotations or co-registered RGB-thermal pairs, enabling robots to per…
This work reports ondeveloping a deep inverse reinforcement learning method for legged robots terrain traversability modeling that incorporates both exteroceptive and proprioceptive sensory data. Existing works use robot-agnostic exteroceptive environmental features or handcrafted kinematic features
Real-time kinodynamic trajectory planning in dy-namic environments is critical yet challenging for autonomous driving. In this paper, we propose an efficient trajectory plan-ning system for autonomous driving in complex dynamic sce-narios through iterative and incremental path-speed optimization. Ex…
High-Definition (HD) maps can provide precise geometric and semantic information of static traffic environments for autonomous driving. Road-boundary is one important information presented in HD maps since it distinguishes between road areas and off-road areas, which can guide vehicles to drive with
Online insurance is a new type of e-commerce with exponential growth. An effective recommendation model that maximizes the total revenue of insurance products listed in multiple customized sales scenarios is crucial for the success of online insurance business. Prior recommendation models are ineffe…
This paper presents a beampattern synthesis scheme based on the single-point array response control with minimum pattern deviation (SPARC-MPD) method. The central concept of SPARC-MPD stems from adaptive array theory, and a closedform expression of the designed weight vector is devised. Comparing to…
This article develops a Bayesian continuous 3D semantic occupancy map from noisy point clouds by generalizing the Bayesian kernel inference model for building occupancy maps, a binary problem, to semantic maps, a multi-class problem. The proposed method provides a unified probabilistic model for bot
Coprime arrays are a class of sensor arrays that play a crucial role in various signal processing tasks because of their desirable properties such as sparsity and increased degrees of freedom (DOF) of coarrays. In this contribution, a new class of three-dimensional (3D) arrays is constructed from pu…
The essence of most shape registration algorithms is to find correspondences between two point clouds and then to solve for a rigid body transformation that aligns the geometry. The main drawback is that the point clouds are obtained by placing the sensor at different views; consequently, the two ma
The factor graph framework is a convenient modeling technique for robotic state estimation where states are represented as nodes, and measurements are modeled as factors. When designing a sensor fusion framework for legged robots, one often has access to visual, inertial, joint encoder, and contact…
State-of-the-art robotic perception systems have achieved sufficiently good performance using Inertial Measurement Units (IMUs), cameras, and nonlinear optimization techniques, that they are now being deployed as technologies. However, many of these methods rely significantly on vision and often fai…