CMTS synthesizes near-miss driving scenarios for safer autonomous driving tests.
problem Lack of near-miss driving data for testing autonomous driving algorithms.
method Generative model conditioned on road maps, using Variational Bayesian methods.
result Synthesized data covers more near-miss scenarios, improving trajectory prediction and risk handling.
H-ReIL learns to drive safely in near-accident scenarios.
problem Driving safely in high-risk near-accident situations.
method Hierarchical RL and IL approach.
result High-level policy switches between low-level policies for safe driving.
D2-City is a diverse traffic dataset for AI development.
problem Lack of comprehensive, detailed datasets for AI in driving.
method Collects over 10,000 dashcam videos with detailed annotations.
result Advances AI in driving perception and related areas.
The paper evaluates Bayesian neural networks for safety in autonomous driving.
problem Safety guarantees for deep neural network controllers in autonomous driving.
method Developed a framework using a state-of-the-art simulator to evaluate Bayesian controllers.
result Bayesian inference methods can provide statistical guarantees for uncertainty computation in autonomous driving.
Study improves self-driving safety in dynamic environments.
problem Safe self-driving in non-stationary urban settings.
method Neurosymbolic Meta-Reinforcement Lookahead Learning (NUMERLA).
result Self-driving agents can adapt safely in real-time.
Accurately predicting the possible behaviors of traffic participants is an essential capability for future autonomous vehicles. The majority of current researches fix the number of driving intentions by considering only a specific scenario. However, distinct driving environments usually contain various possible driving…
HighD dataset captures naturalistic vehicle behavior on German highways for automated driving validation.
problem Current measurement methods fail to meet requirements for scenario-based validation of highly automated vehicles.
method Aerial perspective data collection fulfilling naturalistic behavior, quantity, and variety requirements.
result 16.5 hours of measurements from six locations, 110,000 vehicles, 45,000 km driven, 5600 lane changes.
End-to-end framework classifies cognitive workload in real-time driving scenarios.
problem Challenging task of classifying human cognitive states from behavioral and physiological signals.
method End-to-end framework using mixture Hyper Long Short Term Memory Networks (HyperNetworks).
result Framework outperforms previous methods with 83.9% precision and 87.8% recall.
Simple physical modifications can fool autonomous driving systems.
problem Vulnerability of autonomous driving models to adversarial attacks.
method Demonstrated end-to-end attacks on autonomous driving using simple physical modifications.
result Simple physical modifications can induce activation patterns similar to different scenarios used in training, fooling autonomous driving models.
Deep RL for autonomous highway driving avoids unexpected scenarios.
problem Unexpected scenarios in AV operation space lead to poor decision-making.
method Deep reinforcement learning with safety checks for decision-making.
result Enhanced learning efficiency and safe behavior in highway driving.
The paper explores new risk models for autonomous driving.
problem Risk management and actuarial modeling for autonomous vehicles.
method Examines technical difficulties and proposes a novel risk model.
result The new model better reflects real-world driving safety.
Researchers develop PAIN to improve self-driving safety through adversarial training.
problem Overfitting and poor generalizability of neural networks in self-driving vehicles.
method PAIN combines adversarial training in CARLA simulation to generate edge cases.
result Trained self-driving vehicles are more resilient to environmental uncertainty and less prone to collisions.
A method predicts driving intentions of human-driven vehicles for safer autonomous driving.
problem Predicting timely driving intentions of human-driven vehicles for autonomous vehicles in mixed traffic.
method A Hidden Markov Model (HMM) approach using continuous mobility features.
result HMMs trained with continuous mobility features improve prediction accuracy.
Proposes a method to model multi-vehicle interactions using Gaussian processes.
problem Challenges in modeling correlations between multiple road users over time.
method Uses a stochastic vector field model and non-parametric Bayesian learning.
result Captures motion patterns from complex multi-vehicle interactions without heroic prior assumptions.
ApolloRL offers a platform for RL research in autonomous driving.
problem Improving reinforcement learning for autonomous driving.
method Open platform with training, simulation, and evaluation components.
result Baseline agents perform well in the ApolloRL environment.
Semantically understanding complex drivers' encountering behavior, wherein two or multiple vehicles are spatially close to each other, does potentially benefit autonomous car's decision-making design. This paper presents a framework of analyzing various encountering behaviors through decomposing driving encounter data …
Proposes a generic prediction architecture for autonomous vehicles considering both rational and irrational driving behaviors.
problem Accurately predicting future behaviors of surrounding vehicles for safe autonomous vehicle planning.
method Combines learning-based and planning-based models to address rationalities in human behavior.
result Stable prediction performance under various unseen driving scenarios.
A hybrid model combines Q-learning and PID controller for continuous vehicle control.
problem Learning unsatisfactory results with discrete action space in autonomous driving.
method Combining Q-learning and PID controller, using Quadratic Q-function approximation and action network.
result Autonomous vehicle successfully learns smooth and efficient driving behavior.
Generates multimodal safety-critical scenarios for robustness evaluation of decision-making algorithms.
problem Lack of comprehensive evaluation of neural network robustness under real-world scenarios.
method Proposes a flow-based multimodal scenario generator using weighted likelihood maximization and gradient-based sampling.
result Demonstrates improved testing efficiency and multimodal modeling capability compared to traditional methods.
WiseMove framework for safe deep RL in autonomous driving.
problem Ensuring safety in deep reinforcement learning for autonomous driving.
method Modular learning architecture for motion planning.
result Demonstrated on a common traffic scenario, WiseMove supports safe learning.
End-to-end autonomous driving models are vulnerable to simple physical manipulations of images.
problem Vulnerability of end-to-end autonomous driving models to subtle adversarial manipulations of images.
method Developed novel end-to-end attacks using simple physical manipulations (painting black lines on the road) and used Bayesian Optimization to efficiently search for successful attacks.
result Simple physical manipulations can cause autonomous driving models to follow unintended paths, highlighting the vulnerability of these models.
Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully applied in automotive applications. Motivated by the successful demonstrations of…
Proposes a method for translating synthetic images to real-world scenarios.
problem Ill-posed nature of unpaired image-to-image translation.
method Explicitly enforce preservation of ground-truth labels on translated images.
result Significantly improved performance over state-of-the-art model for semantic segmentation.
Proposes novel method for detecting novel scenarios in autonomous systems.
problem Detecting when a machine learning model makes a trustworthy prediction in dynamic, real-world situations.
method Leverages trained model's learned information and a new image similarity metric.
result Demonstrates the method's efficacy on real-world driving and indoor racing datasets.
Extends driving model to control agent behavior in simulations.
problem Simulate realistic driving behavior for autonomous systems.
method Introduces Control-ITRA method to influence agent behavior through waypoint assignment and target speed modulation.
result Demonstrates controllable, infraction-free trajectories while preserving realism.
MIDAS learns to adaptively control other cars in urban driving scenarios.
problem Autonomous vehicles need to interact with other agents on the road.
method Reinforcement learning with attention mechanism to handle multiple agents.
result MIDAS policies are adaptive and robust to external changes.
Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured urban roadways. Since there are many possible scenarios, manually tackling all po…
IDAS approach for autonomous vehicles to make decisions under merging scenarios.
problem Decision making for autonomous vehicles in merging scenarios with varying driver cooperativeness.
method IDAS approach using multi-agent reinforcement learning (MARL) with curriculum learning and masking mechanism.
result IDAS approach can handle uncertainties in real-world scenarios and make strategic decisions.
This review covers methods for autonomous driving including tracking, prediction, and decision making.
problem Improving autonomous driving through better tracking, prediction, and decision making.
method Approaches based on neural networks, stochastic techniques, and reinforcement learning are discussed.
result Effective methods for autonomous driving are identified and compared.
New approach uses dynamic programming to efficiently discover failures in autonomous vehicle simulations.
problem Efficiently discovering rare failure events in autonomous vehicle simulations.
method Approximate dynamic programming and scene decomposition to estimate failure distribution.
result Increased number of failures discovered compared to baseline approaches.
This work trains a model to predict human driving directions from road scenes.
problem Defining implicit rules of human behavior for autonomous vehicles.
method Self-supervised learning of probabilistic network model.
result Model successfully generalizes to new road scenes.
The paper uses deep reinforcement learning to control autonomous lane changes safely.
problem Safe and efficient autonomous lane changes in vehicles.
method Deep Q-networks and quadratic approximators for decision-making and control.
result Demonstrated effectiveness in simulations for decision-making and control.
Two autoencoding models learn latent traffic scene representations.
problem Learning latent representations of traffic scenarios.
method CNN and RNN models for spatio-temporal and temporal data, incorporating permutation invariance.
result Latent scenario embeddings can be used for clustering and similarity retrieval.
Deep Q-learning analyzes EEG for drowsiness during driving tests.
problem Estimating drowsiness during driving to improve safety.
method Adapting Q-learning to EEG data for drowsiness estimation.
result Trained model accurately tracks mind state variations in EEG data.
Deep Recurrent Q-Network improves autonomous driving in urban areas with pedestrians.
problem Challenges in urban autonomous driving due to complex road structures and unpredictable pedestrian behavior.
method Combines Deep Q-Network with LSTM for long-term memory, designed a 3-D state representation, and uses a reward function.
result The proposed DRQN-based approach outperforms rule-based methods in dense urban scenarios.
Paper proposes methods to help autonomous vehicles adapt to unexpected driving scenarios.
problem Autonomous vehicles struggle with unexpected driving conditions.
method Robust imitative planning (RIP) and adaptive robust imitative planning (AdaRIP) methods to detect and adapt to distribution shifts.
result Methods outperform current state-of-the-art approaches in nuScenes prediction challenge.
SECRM-2D improves RL-based autonomous driving with safety guarantees.
problem Safety and efficiency trade-offs in RL-based autonomous driving.
method RL-based controller with safety constraints for efficient and comfortable driving.
result SECRM-2D avoids crashes and improves efficiency and comfort compared to baselines.
Deep neural network detects driver intentions from video.
problem Detecting driver intentions for safer self-driving.
method Uses deep learning to analyze turn signals and emergency flashers.
result High per-frame accuracy in challenging scenarios.
ACOL learns constraints from human preferences in driving simulations.
problem Learning constraints from human preferences in driving simulations.
method Adaptive Constraint Learning (ACOL) algorithm for constrained linear best-arm identification.
result ACOL's sample complexity matches worst-case lower bound and is significantly tighter in the average case.
Adaptive vehicle trajectory prediction for safer autonomous driving.
problem Inability of current methods to guarantee physical feasibility and adapt to human driving policies.
method Bayesian recurrent neural network combining policy and physical models, with gradient-based training and parameter adaptation.
result The proposed method ensures physical feasibility and adaptability to human driving policies.
Deep learning predicts vehicle behavior for safer autonomous driving.
problem Enhance autonomous vehicles' hazard awareness in complex environments.
method Review of deep learning-based approaches for vehicle behaviour prediction.
result Deep learning outperforms conventional methods in complex scenarios.
Autonomous vehicles (AVs) are on the road. To safely and efficiently interact with other road participants, AVs have to accurately predict the behavior of surrounding vehicles and plan accordingly. Such prediction should be probabilistic, to address the uncertainties in human behavior. Such prediction should also be in…
Deep RL agent improves lane changing in unpredictable traffic.
problem Uncertainty in other drivers' behaviors and safety vs agility trade-off.
method Developed a deep reinforcement learning agent in a simulated highway environment.
result Significantly better performance in noisy environments compared to heuristic methods.
Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.
problem Unexplainable behaviours and lack of safety guarantees in RL for real vehicles.
method PCPO framework with trust regions and parallel learners.
result Safe learning confirmed for autonomous vehicles with fast convergence.
Hybrid Bayesian MOT uses neural networks to improve model aspects, achieving state-of-the-art performance.
problem Improving multiobject tracking performance across various scenarios.
method Hybrid approach combining neural network enhancements with Bayesian estimation and belief propagation.
result State-of-the-art performance in autonomous driving dataset evaluation.
Adversarial attacks pose a threat to deep neural networks, especially in safety-critical applications.
problem Adversarial attacks can misclassify deep neural networks, leading to safety issues.
method Adversarial attacks are categorized into white-box and black-box attacks based on the attacker's knowledge. They can be targeted or non-targeted.
result Adversarial attacks are effective and can transfer between different models and real-world scenarios.
PIP-Net predicts pedestrian crossing intentions with up to 4-second lead.
problem Accurate pedestrian intention prediction for autonomous vehicles in real-world scenarios.
method Recurrent and temporal attention-based model using kinematic and spatial features.
result PIP-Net predicts pedestrian crossing intentions up to 4 seconds in advance.
A framework clusters vehicle motion trajectories efficiently.
problem Costly manual annotation of vehicle motion data.
method Five-stage framework: align, embed, extract, embed, cluster.
result Framework achieves promising results on real-world dataset.