#autonomous driving
11 resultsPixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
Yuhu Shan, Wen Feng Lu, Chee Meng Chew
The paper proposes an unsupervised domain adaptation framework for object detection in autonomous driving that combines pixel‑level image translation using GANs and cycle consisten…
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
Garrick Brazil, Xiaoming Liu
The paper introduces M3D-RPN, a monocular 3D region proposal network that uses depth‑aware convolutions to estimate 3D bounding boxes from a single image, improving detection perfo…
Agile Autonomous Driving using End-to-End Deep Imitation Learning
Yunpeng Pan, Ching-An Cheng, Kamil Saigol +4
The paper introduces an end-to-end deep imitation learning system that enables high-speed off‑road autonomous driving using only low‑cost sensors, by training a neural network to m…
Incremental Reinforcement Learning --- a New Continuous Reinforcement Learning Frame Based on Stochastic Differential Equation methods
Tianhao Chen, Limei Cheng, Yang Liu +2
The paper introduces Incremental Reinforcement Learning (IRL), a continuous reinforcement‑learning framework built on stochastic differential equations that ensures action continui…
Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants
Annika Meyer, Jonas Walter, Martin Lauer +1
The paper proposes a method for automated vehicles to infer lane-level intersection layouts directly from observed trajectories of other traffic participants, without relying on pr…
Mono-Stixels: Monocular depth reconstruction of dynamic street scenes
Fabian Brickwedde, Steffen Abraham, Rudolf Mester
The paper proposes mono-stixels, a compact representation that estimates depth, motion, and semantic information from a monocular video of dynamic street scenes using optical flow,…
Learning Guided Convolutional Network for Depth Completion
Jie Tang, Fei-Peng Tian, Wei Feng +2
The paper introduces a guided convolutional network that predicts spatially‑variant kernels from an RGB image to fuse sparse LiDAR depth with visual guidance, using a factorized co…
Scalable Place Recognition Under Appearance Change for Autonomous Driving
Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin +3
The paper introduces a scalable place recognition method for autonomous driving that can be efficiently retrained and compressed to handle continuous appearance changes without inc…
Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
Tianyang Zhao, Yifei Xu, Mathew Monfort +5
The paper introduces a Multi-Agent Tensor Fusion network that jointly models agents' past trajectories, social interactions, and scene context to predict future movements for auton…
Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems
Kaite Xiang, Kaiwei Wang, Kailun Yang
The paper introduces an importance‑aware loss function and two efficient pyramidal context networks (ERF‑PSPNet and BiERF‑PSPNet) to improve semantic segmentation for navigation‑as…
nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems
Chih-Hong Cheng, Chung-Hao Huang, Georg Nührenberg
The paper introduces nn-dependability-kit, an open‑source toolbox that helps engineers assess and improve the safety of neural networks used in autonomous driving by providing depe…