Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 17 of 17 for “"motion forecasting"”.
-
Motion forecasting for autonomous driving in a streaming world
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01
-
Deep Learning Solutions for Perception and Motion Forecasting in Autonomous Vehicles
… accurate and real-time perception, tracking, and motion forecasting necessary to navigate safely through complex and dynamic environments. These systems must be able to intuitively make decisions within split seconds in an urban environment with multiple agents interacting. This thesis proposes a …
-
Typhoon motion forecasting using empirical orthogonal function analysis of the synoptic forcing
Empirical Orthogonal Function (EOF) analysis is used to describe the synoptic forcing features of selected northwestern Pacific Ocean tropical cyclones from 1967 to 1976. EOF analysis is applied to the geopotential field at 850, 700 and 500mb on a 120 point grid with 5 degree latitude and longitude …
-
Modelling Pedestrians in Autonomous Vehicle Testing
… in deployment. The majority of AV trajectory forecasting literature do not utilize the motion cues present in 3D human pose because it is hard to gather large datasets of articulated 3D pedestrian motion. In this thesis we discuss the difficulties in data gathering and propose a pedestrian …
-
Generative modeling of topological and spatiotemporal data
… with continuous geometry, and human or driving motion evolves through interacting agents under uncertainty. This dissertation develops generative models for topological, hybrid, and spatiotemporal data by adapting how these models represent, learn, and sample structured distributions. The first …
-
Motion Planning for Driverless Shuttles, Passenger Cars, and Trucks
… is planning a safe, comfortable, and efficient motion in complex, real-world environments. This thesis addresses motion planning across three distinct domains: urban shuttles, passenger vehicles, and truck-trailer systems. It contributes practical insights and novel approaches toward scalable …
-
3D reconstruction and scene understanding with 3D Gaussian Splatting representation
… scene reconstruction, semantic reasoning, and motion forecasting in autonomous driving scenarios. Finally, we explore the potential of 3D Gaussian representations for interactive scene manipulation. We propose 3DSceneEditor, a fully 3D-based framework that enables controllable and semantically …
-
RecTTA: Reconstruction-based Test-Time Adaptation For Robust Trajectory Prediction In Dynamic Environments
… conditions, sensor characteristics, and motion patterns that inevitably arise during deployment. This limitation undermines reliability precisely when accurate predictions are most critical for safety-critical autonomous systems. This thesis introduces RecTTA (Reconstruction-based …
-
Enhancing Probabilistic Compound Flood Inundation Mapping Through Improved Boundary Conditioning in 2D Hydrodynamic Models
… advances probabilistic compound flood forecasting by developing integrated frameworks that quantify and reduce forcing and boundary uncertainties, utilizing the highly urbanized Houston-Galveston Bay region as a primary case study.First, a Global Copula-embedded Bayesian Model Averaging …
-
Perception and Prediction in Multi-Agent Urban Traffic Scenarios for Autonomous Driving
… a self-supervised learning approach for motion forecasting in autonomous driving that enhances accuracy and generalizability without compromising inference speed or model simplicity, utilizing pseudo-labels from pretext tasks for learning transferable motion patterns. (ii) The second …
-
Label-efficient learning paradigms for scalable robot perception
… key downstream tasks such as path planning, motion forecasting, and collision avoidance. However, learning such representations typically relies on dense and expensive forms of supervision such as 3D occupancy grids, bird's-eye view maps, and 3D object trajectories. Obtaining such annotations …
-
Driving Behavior Analysis and Prediction for Safe Autonomous Vehicles
… by introducing three novel prediction models for forecasting drivers intentions and behaviors at unsignalized intersections. We then address social reasoning by proposing a novel prediction model that analyzes agent interactions using graph neural networks, making the scene understanding process …
-
3D Deep Learning for Object-Centric Geometric Perception
… These attributes include shape, pose, and motion of the target objects, which enable fine-grained object-level understanding for various tasks in graphics, computer vision, and robotics. With the growth of 3D geometry data and 3D deep learning methods, it becomes more and more likely to …
-
On the motion and action prediction using deep graph models
Motion and action prediction is a crucial component of autonomous systems and robotics. This component is vital for accidents predictions or prevention, motion planning, surveillance systems and behavior analysis. Typically, the problem involves the observation of multiple agents’ motion or actions …
-
Methods for Learning the Language of Behavior: Observing, Representing, and Predicting Action
… the mapping across viewpoints with a markerless motion capture system built from 62 synchronized cameras that reconstructs 13 body landmarks in 3D for freely moving macaques. Multiview geometry propagates a small set of hand annotations across the remaining views, cutting annotation effort by a …