Paper predicts driver actions using deep neural networks.
problem Predicting driver actions for safer driving.
method Formulated as timeseries anomaly prediction, uses DBRNN to learn correlations.
result Achieves accurate action prediction up to 5 seconds in advance.
Study predicts individual treatment effects in ride-sharing competitions.
problem Understanding how team competitions affect individual drivers' outcomes.
method Analyzed data from 500 competitions, built machine learning models.
result Reduced out-sample prediction error by over 24%.
Method learns driver behavior from synthetic data.
problem Learning driver behavior from unobservable variables.
method Simultaneous policy learning and latent state inference.
result Effective driving policies learned without direct class knowledge.
ProMoD models human race drivers with probabilistic movement primitives and neural networks.
problem Challenging task of modeling human driver behavior due to variability and complexity.
method Modular framework with Probabilistic Movement Primitives, clothoids, and neural networks.
result Significant advantages in imitation accuracy and robustness compared to other algorithms.
Improved driver identification accuracy using steering wheel data.
problem Accurately identifying drivers based on naturalistic driving behavior.
method Novel approach for window length parameter design, leveraging GRUs neural network.
result Increased driver identification accuracy from under 15% to over 65%.
Real-time drowsiness detection on mobile phones reduces road trauma.
problem Driver drowsiness increases crash risk and road trauma.
method Depthwise separable 3D convolutions combined with early fusion of spatial and temporal information.
result Real-time drowsiness detection on mobile phones reduces road trauma.
Bitcoin's price direction is better predicted without additional drivers during high volatility.
problem Predicting Bitcoin's price direction using various determinants.
method Continuous local transfer entropy for feature selection and deep learning classification model.
result Bitcoin's price direction can be better predicted without additional drivers during high volatility.
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.
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.
The paper identifies drivers from a single car turn using sensor data.
problem Predicting driver identity from a single car turn using sensor data.
method Time series classification of sensor readings from a single turn, focusing on unique patterns in each driver's style.
result Accurate identification of drivers from a single turn, even in varied driving conditions.
A method for training autonomous vehicles using continuous human feedback to avoid sub-optimal decisions.
problem Training autonomous vehicles with limited and potentially sub-optimal human demonstrations.
method Continuous scalar feedback for each action to learn from sub-optimal demonstrations and evaluative feedback.
result The proposed method outperforms supervised learning on positive examples alone and learns from sub-optimal demonstrations.
DA-RNN predicts driving maneuvers up to 3 seconds ahead.
problem Adapting driving model to new drivers and vehicles.
method Domain-Adversarial Recurrent Neural Network (DA-RNN) for robust predictions.
result DA-RNN improves performance by 30% in real drivers and 114% in simulations.
End-to-end model predicts multiagent trajectories using game theory and neural nets.
problem Predicting trajectories of interacting agents in complex scenarios.
method Hybrid neural net with game-theoretic reasoning, using implicit layers to map preferences to Nash equilibria.
result Trains an interpretable model that predicts future trajectories and transfers to decision making.
Comma.ai's approach to Artificial Intelligence for self-driving cars is based on an agent that learns to clone driver behaviors and plans maneuvers by simulating future events in the road. This paper illustrates one of our research approaches for driving simulation. One where we learn to simulate. Here we investigate v…
Paper predicts future vehicle trajectories for safer AVs.
problem Improving accuracy of long-term vehicle trajectory prediction for autonomous vehicles.
method Dual LSTM network for automatic learning of driver behaviors and future trajectory prediction.
result The method achieves lower RMSE for longitudinal and lateral predictions compared to state-of-the-art methods.
Study develops a cost model for field canals improvement projects in Egypt.
problem Accurately predict the preliminary costs of field canals improvement projects.
method Developed a parametric cost model using machine learning methods.
result Identified key cost drivers and developed a model for FCIPs.
New numerical methods for pricing American options using semilinear BSDEs.
problem Pricing American options with complex payoff functions in multi-dimensional settings.
method Proposed two numerical schemes based on branching processes and randomization.
result Simple randomization provides good results for approximating discontinuous drivers.
New machine learning model identifies key drivers of market troughs.
problem Misrepresentation of market trough drivers by simpler models.
method Flexible DML average partial effect causal machine learning framework.
result Volatility of options-implied risk appetite and market liquidity are key drivers.
Facial landmark localization and occlusion estimation for driver safety.
problem Robust facial landmark localization and occlusion estimation under harsh lighting and occlusion.
method Occluded Stacked Hourglass approach based on Stacked Hourglass network.
result State-of-the-art results in face detection, head pose, and occlusion estimation on various datasets.
Improved logistic models for better interpretability in regulated industries.
problem Limited interpretability in machine learning models for regulated industries.
method Blend logistic regression with machine learning techniques for enhanced interpretability.
result Solid performance with minimal analyst effort and enhanced interpretability.
Modeling driver behavior using GPS data and HDP split-merge sampling.
problem Understanding individual driver behaviors and road network from GPS data.
method Hidden Markov Model (HMM) and Hierarchical Dirichlet Process (HDP) with split-merge sampling.
result Data-driven predictions about destinations and road conditions.
Study dynamic portfolio choice under rotating drivers, revealing a new geometric structure.
problem Investment under changing drivers with mutual independence.
method Analyzes geometric structure of portfolio choice, focusing on drivers and their rotation.
result Optimal policy separates into static and hedging components, reflecting the dynamic nature of drivers.
This paper improves route choice models by incorporating contextual factors.
problem Existing route choice models lack consideration of dynamic contextual conditions.
method Knowledge distillation from Stated Choice Experiments in Immersive Virtual Environment.
result High-fidelity route choice models with increased predictive power.
A rapid pattern-recognition approach to characterize driver's curve-negotiating behavior is proposed. To shorten the recognition time and improve the recognition of driving styles, a k-means clustering-based support vector machine ( kMC-SVM) method is developed and used for classifying drivers into two types: aggressiv…
A new method selects robust features for ML models using causal discovery.
problem Challenges in feature selection for ML models with limited domain knowledge.
method Multidata causal feature selection using PC1 or PCMCI algorithms.
result The method improves model performance and provides interpretable drivers.
Method compares driver performance using behavioral advantage, removing environmental factors.
problem Challenging to analyze human driver or autonomous vehicle performance quantitatively.
method Uses driver behavioral advantage to compare performance across different environmental conditions.
result Evaluated and ranked the performance of over 100 truck drivers in terms of fuel efficiency.
Improved risk assessment for UBI using telematics data and AdaBoost.
problem Class imbalance in predicting claims frequency for UBI.
method Cost-sensitive multi-class AdaBoost (SAMME.C2) algorithm.
result SAMME.C2 outperforms other models in handling class imbalances.
Long-term lane change prediction model predicts maneuvers with 75% accuracy.
problem Predicting long-term lane changes for safer autonomous driving.
method Introduced three models: logistic regression, MLP, and RNN. Used NGSIM dataset with new labeling scheme.
result Developed model predicts 75% of lane changes with an average advanced time of 8.05 seconds.
New method identifies drivers from car logs without reverse-engineering CAN protocol.
problem Identifying drivers from in-vehicle network logs without access to exact signal semantics.
method Machine learning techniques applied to off-the-shelf data.
result Driver re-identification accuracy of 75-85% on a dataset of 33 drivers.
Optimizes e-hailing drivers' passenger seeking to reduce congestion and pollution.
problem Reduces congestion and pollution by optimizing e-hailing drivers' passenger seeking.
method Uses Markov Decision Process (MDP) and imitation learning to model and optimize drivers' decisions.
result Achieves a 17.5% improvement in passenger return rate over a heuristic strategy.
Optimizes portfolios by identifying causal drivers of diversification.
problem Achieving efficient portfolio optimization based on asset and diversification dynamics.
method Commonality Principle, Reichenbach Common Cause Principle, conformal maps, Bayesian networks, correlation-based algorithms, neural networks, SDEs.
result Optimal portfolio diversification achieved through causal methodologies and sensitivity forecasting.
Improved vehicle motion prediction with uncertainty estimation.
problem Robust motion prediction for autonomous vehicles, especially under distributional shift.
method Presented an approach significantly improving the benchmark and taking 2nd place on the leaderboard.
result Significantly improved motion prediction and uncertainty measurement.
Study shows cryptocurrency market impact on DeFi returns stronger than other drivers.
problem Understanding drivers of DeFi returns and their relative importance.
method Investigated four drivers: cryptocurrency market exposure, network effect, investor attention, and valuation ratio. Designed a new market index, DeFiX.
result Cryptocurrency market impact on DeFi returns is stronger than other drivers and provides superior explanatory power.
The paper proposes a machine learning method to detect drivers' affective states using physiological signals.
problem Detecting and assessing drivers' affective states to improve driving safety and well-being.
method Multiview multi-task machine learning approach using physiological signals.
result Accounting for drive-specific differences significantly improves model performance.
Study finds telemetric data not effective for predicting truck accident risk.
problem Estimating the risk of truck accidents using telemetric data.
method Used machine learning approaches: Random Forests and Convolutional Neural Networks.
result Neither approach successfully predicted truck accident risk.
CPCMs integrate causal drivers for robust portfolio optimization.
problem Degradation of classical portfolio models under structural breaks and lack of arbitrage consistency in machine learning.
method Causal PDE-Control Models integrating structural causal drivers, nonlinear filtering, and forward-backward PDE control.
result CPCM solvers achieve higher Sharpe ratios and lower turnover than benchmarks.
Paper tackles modeling TVCNs with unknown drivers and partial data.
problem Modeling and understanding TVCNs with unknown drivers and partial data.
method Generalized modeling approach of TVCNs using fractional dynamical equations and iterative framework.
result Proposed framework successfully predicts state of the system using real EEG data.
Optimizes portfolios using neural network approximations of asset sensitivities to common drivers.
problem Optimizing portfolios with complex asset dynamics and common drivers.
method Model asset dynamics with PDEs, approximate sensitivities with neural networks, and use hierarchical clustering on sensitivity matrix for optimization.
result Achieves over-performance in portfolio optimization across various markets and datasets.
Proposes a simple method to explain aleatoric uncertainty in neural networks.
problem Lack of transparent explanations for uncertainty estimates in AI models.
method Adapting a neural network with Gaussian output to estimate predictive variance and applying explainers to the variance output.
result The proposed method explains uncertainty more reliably than complex approaches and outperforms them in most settings.
PRECOG predicts future interactions between AVs and other drivers.
problem Autonomous vehicles need to predict human drivers' intentions for safe road behavior.
method Probabilistic forecasting model trained on real and simulated data.
result Our model predicts future interactions more accurately than existing methods.
TNDE quantifies dynamic gene drivers from single-cell snapshots.
problem Reconstructing time-resolved regulatory effects in biological processes.
method Time-varying Network Driver Estimation (TNDE) using shared graph attention encoder and partial optimal transport.
result TNDE identifies stage-specific driver genes in mouse erythropoiesis.
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.
Paper proposes personalized climate control for driver comfort.
problem Limited research on in-vehicle climate control and driver preferences.
method IoT platform for data collection, machine learning for driver behavior recognition, and personalized preference recommendation.
result Prototype demonstrates effective and accurate climate control for driver comfort.
The paper studies ABSDEs with jumps and various growth drivers.
problem Solving ABSDEs with specific growth conditions.
method Proves existence of unique solution for ABSDEs with jumps and various growth drivers.
result Existence of unique solution for ABSDEs with specific growth conditions.
This paper optimizes driver repositioning using MARL and reward design for better service and traffic management.
problem Unserved passenger requests due to drivers' cruising behavior during passenger seeking.
method Mean field multi-agent reinforcement learning (MARL) with a reward design scheme and Bayesian optimization (BO) to solve bilevel optimization problems.
result Optimal toll charges and service charges can improve platform and city planner objectives by significant margins, leading to better traffic conditions.
Deep RL tackles fleet management and dispatching for ride-sharing platforms.
problem Optimizing dispatching and repositioning of drivers in ride-sharing platforms.
method Deep reinforcement learning approach treating drivers as a central system agent.
result Centralized decision-making improves overall fleet efficiency.
The paper develops a faster surrogate model for simulators using hybrid methods.
problem The need for faster validation of automotive technologies using simulators.
method Testing classical methods and building hybrid models combining them.
result A hybrid surrogate model outperforms classical methods in multivariate time series prediction.
Safe imitation learning with a safety layer for flexible training.
problem Flexible yet safe imitation learning for complex tasks.
method Theory and modular method with a safety layer for continuous policy, adversarial training, and worst-case safety guarantees.
result Robustness advantage of safety layer during training compared to test time.