Related papers: PrevPredMap: Exploring Temporal Modeling with Prev…
Nowadays, our mobility systems are evolving into the era of intelligent vehicles that aim to improve road safety. Due to their vulnerability, pedestrians are the users who will benefit the most from these developments. However, predicting…
While bird's-eye-view (BEV) perception models can be useful for building high-definition maps (HD-Maps) with less human labor, their results are often unreliable and demonstrate noticeable inconsistencies in the predicted HD-Maps from…
Accurate environmental representations are essential for autonomous driving, providing the foundation for safe and efficient navigation. Traditionally, high-definition (HD) maps are providing this representation of the static road…
Temporal set prediction involves forecasting the elements that will appear in the next set, given a sequence of prior sets, each containing a variable number of elements. Existing methods often rely on intricate architectures with…
Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned…
Detectors with high coverage have direct and far-reaching benefits for road users in route planning and avoiding traffic congestion, but utilizing these data presents unique challenges including: the dynamic temporal correlation, and the…
Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these…
Data Prefetching is a technique that can hide memory latency by fetching data before it is needed by a program. Prefetching relies on accurate memory access prediction, to which task machine learning based methods are increasingly applied.…
Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to…
Effectively modeling non-stationary dynamics in probabilistic multivariate time series(MTS) forecasting requires balancing expressiveness with robustness. Existing parametric approaches benefit from strong inductive biases but lack…
Online map generation and trajectory prediction are critical components of the autonomous driving perception-prediction-planning pipeline. While modern vectorized mapping models achieve high geometric accuracy, they typically treat map…
Most autonomous cars rely on the availability of high-definition (HD) maps. Current research aims to address this constraint by directly predicting HD map elements from onboard sensors and reasoning about the relationships between the…
While recent online HD mapping methods relieve burdened offline pipelines and solve map freshness, they remain limited by perceptual inaccuracies, occlusion in dense traffic, and an inability to fuse multi-agent observations. We propose…
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to…
Constructing online High-Definition (HD) maps is crucial for the static environment perception of autonomous driving systems (ADS). Existing solutions typically attempt to detect vectorized HD map elements with unified models; however,…
Our work explores the task of generating future sensor observations conditioned on the past. We are motivated by `predictive coding' concepts from neuroscience as well as robotic applications such as self-driving vehicles. Predictive video…
Camera-based 3D object detection and tracking are central to autonomous driving, yet precise 3D object localization remains fundamentally constrained by depth ambiguity when no expensive, depth-rich online LiDAR is available at inference.…
Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future…
Despite tremendous advancements in bird's-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information…
Networks representation aims to encode vertices into a low-dimensional space, while preserving the original network structures and properties. Most existing methods focus on static network structure without considering temporal dynamics.…