Multimodal Input-Dependent Object Query Initialization for LiDAR-Camera 3D Object Detection with Transformers

3D object detection models that exploit both LiDAR and camera sensor features are top performers in large-scale autonomous driving benchmarks. A transformer is a popular network architecture used for this task, in which so-called object queries act as candidate objects. Initializing these object queries based on current sensor inputs leads to...

Ultrasonic perception for autonomous vehicles

With recent advancements in autonomous driving, the demand for precise and accurate perception systems has increased. Perception of the vehicle’s environment is a key element in ensuring safe operation. Due to their wide aperture angle and low cost, ultrasonic sensors are a viable option for achieving close-range 360° perception around the...

Comparative Analysis of Exploration Algorithms in Deep Reinforcement Learning for Autonomous Driving: How does epsilon-greedy, random network distillation, bootstrapped DQN affect training and the robustness of final policies under various testing conditions in autonomous driving?

Autonomous driving is a rapidly evolving field that aims to enhance road safety and reduce accidents through the use of advanced software and hardware technologies. Reinforcement learning (RL) combined with deep neural networks has emerged as a promising approach for training autonomous agents. This research paper investigates three exploration...

Sensing and Machine Learning for Automotive Perception: A Review

Automotive perception involves understanding the external driving environment and the internal state of the vehicle cabin and occupants using sensor data. It is critical to achieving high levels of safety and autonomy in driving. This article provides an overview of different sensor modalities, such as cameras, radars, and light detection and...

Learning from Demonstrations of Critical Driving Behaviours Using Driver’s Risk Field

In recent years, imitation learning (IL) has been widely used in industry as the core of autonomous vehicle (AV) planning modules. However, previous work on IL planners shows sample inefficiency and low generalisation in safety-critical scenarios, on which they are rarely tested. As a result, IL planners can reach a performance plateau where...

Generalized Single-Vehicle-Based Graph Reinforcement Learning for Decision-Making in Autonomous Driving

In the autonomous driving process, the decision-making system is mainly used to provide macro-control instructions based on the information captured by the sensing system. Learning-based algorithms have apparent advantages in information processing and understanding for an increasingly complex driving environment. To incorporate the...

Targetless Camera-LiDAR Calibration for Autonomous Systems

In recent decades, the field of autonomous driving has witnessed rapid development, benefiting from the development of artificial intelligence-related technologies such as machine learning. Autonomous perception in driving is a key challenge, in which multi-sensor fusion is a common feature. Due to the high resolution and rich information, the...

Mediating between Human Driver and Automation through Human-Machine Interface for Highly Automated Vehicles

This master thesis report gathers the research and design activities executed in 100 working days, in order to investigate the future context of autonomous driving. More specifically, the communication between the human driver and automation during the automated driving modes (Long Out of the Loop and Standby modes) has been investigated to...

Predicting pedestrian path using optical flow as context cue

A human driver can gauge the intention and signals given by other road users indicative of their future behaviour. The intentions and signals are identified by looking at the cues originating from vulnerable road users or their surroundings (hand signals, head orientation, posture, traffic signals, distance to curb, etc.). Taking all these cues...

How Human-Machine Interaction keeps pace with Automated Vehicles: A systematic review

Human Machine Interface (HMI) is a design concept that improves the interaction between the driver and the automated vehicle, which leads to greater safety and comfort for the driver and greater safety for the road user. Therefore, many papers and patents are published every year. Many papers use different methodologies and materials due to some...

Human motion trajectory prediction: a survey

With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand, and anticipate human behavior becomes increasingly important. Specifically, predicting future positions of dynamic agents and planning considering such predictions are key tasks for self-driving vehicles, service...

Highly Automated Driving: Transitions of control authority using Haptic Shared Control

The arrival of highly automated vehicles introduces a new interaction between the vehicle and driver. System limitations during highly automated driving require the driver to be ready to take back control at request.<br/>Previous studies on the take-over process concluded that the driver requires a transition period to stabilize vehicle control...

Longitudinal Control for Autonomous Vehicles: A comparison between Reinforcement Learning and Optimal Control

In the automotive industry automation is popular and every year car OEMs advance their technology to be able to drive autonomously. Longitudinal control of the vehicles is an important part of the complete autonomous driving system. The difficulty of this control problem lies with changing longitudinal dynamics and the lack of full-state system...

Real-life implementation of a GPS-based path-following system for an autonomous vehicle

This work is meant to report on activities at TU Delft on the design and implementation of a path-following system for an autonomous Toyota Prius. The design encompasses: finding the vehicle parameters for the actual vehicle to be used for control design; lateral and longitudinal controllers for steering and acceleration, respectively. The...

Investigating the effect of Autonomous Driving on the interior architecture of a Porsche sports car.

In today’s world, provision of efficient, safe and fun mobility is one of the main challenges in our highly populated and dynamic urban environments. Traditional and passive mobility systems, which only rely on human control inputs are no longer safe and suitable to operate in these highly unpredictable environments. This increasing complexity...