A Personalized Highway Driving Assistance System Saina Ramyar 1 Dr. Abdollah Homaifar 1 1 ACIT Institute North Carolina A&T State University March, 2017 Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 1 / 27
Outline Introduction 1 Background Related Work 2 Personalized Driver Models Maneuver Decision Making and Control Proposed Highway Driving Assistance System 3 Decision Maker Driver Model Control System Simulation and Results 4 Driver Model Driving Scenarios Conclusion and Discussion 5 Future Work 6 Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 2 / 27
Introduction Background Types of Autonomy in Vehicles Semi-Autonomous: Cruise Control, Emergency Braking, Lane Departure Warning Fully Autonomous: Google (Waymo), Tesla self driving cars Shortcomings Majority of autonomous driving systems are focused on safety Maneuvers generated are pre-defined and conservative Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 3 / 27
Motivation Drivers’ Points of View People have various driving styles Conservative driving does not satisfy everyone Interest and trust in autonomous driving will be decreased Solution The autonomous features must be designed according to the drivers’ preferences. Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 4 / 27
Related Work Personalized Driver Models Drivers’ steering input prediction using a transfer function Drivers’ lane-change intent prediction using Relevance Vector Machine (RVM) Disadvantages: Behavior is simplified Environment is simplified Output is given as a recommendation to the driver The model may not perform well in an unseen scenario. Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 5 / 27
Related Work Maneuver Decision Making and Control Maneuver that requires both decision making and control: Lane Change The lane change decision is made to maximize driving safety and quality Optimization methods are employed Mixed integer programming is used for an optimized decision MIP could result in loss of convexity. Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 6 / 27
Proposed Highway Driving Assistance System Proposed Approach: Driver Model + Controller Scenario of Interest: Highway driving It is very close to autonomous driving. System Modes: Most maneuvers on a highway: Path Following Car Following Lane Change The modes are activated according to: Driver’s preference Environment condition These modes can be overridden for a mandatory maneuver (exit). Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 7 / 27
Proposed Highway Driving Assistance System Driver Model Data from an individual driver Random Forest regression is used for modeling driver behavior Control System: Model Predictive Control (MPC) system for tracking arbitrary references Longitudinal motion is studied in order to maintain safe speed and distance with surrounding vehicles Assumptions: Available equipment for autonomous control of vehicle Available data from surrounding vehicles and environment through V2V, V2I and sensors Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 8 / 27
Decision Maker Algorithm Factors for Mode Activation: Vehicle Safety Driver’s Preference Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 9 / 27
Driver Model Pre-processing Input Features: Vehicle Position Vehicle Velocity Target variable: vehicle acceleration All input variables are scaled in the range of [0, 1] Target variable transformed into exponential space Feature Generator d 2 × v d 2 d 3 v 2 d × v 2 v 3 ] F = [ d v v × d (1) Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 10 / 27
Driver Model Random Forest Regression Algorithm Random Forest Regression Algorithm Input: Number of randomly chosen predictors in each split: m try , Number of bootstrap sample: n tree Output: Average of the output of all tree, P 1: for i = 1 to n tree do randomly select m try number of features 2: grow an un-pruned regression tree with m try randomly selected 3: features/predictors choose the best split among these randomly selected predictors 4: 5: end for 6: for a new sample, predict the output of n tree number of trees and average their output. Denote the output as P 7: return P Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 11 / 27
Preliminaries Consider a linear discrete system: x t +1 = Ax t + Bu t (2) In model predictive control (MPC) a constrained optimization is solved at each time instant If the sets X , U are convex, the MPC problem can be solved with Quadratic Programming (QP) U t J = 1 2 w T Hw + d T w min (3a) H in w ≤ K in (3b) H eq w = K e q (3c) Where w = [ U t , x T t +1 , · · · , x T t + N ] Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 12 / 27
MPC for Tracking Dynamic Reference MPC controller for tracking periodic references is used here: V N ( x , r x , r u ; x r , u r , u N ) = V t ( x ; x r , u r , u N ) + V p ( r x , r u ; x r , u r ) (4) Planned Trajectory: Steady state behavior T − 1 � � x r ( i ) − r ( i ) � 2 S + � u r ( i ) − r u ( i ) � 2 V p ( r x , r u ; x r , u r ) = (5) V i =0 Tracking Error: Transient behavior N − 1 � x ( i ) − x r ( i ) � 2 Q + � u ( i ) − u r ( i ) � 2 V t ( x ; x r , u r , u N ) = � (6) R i =0 Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 13 / 27
MPC Formulation MPC for tracking a changing reference V N ( x , r x , r u ; x r , u r , u N ) min (7a) x r , u r , u N x (0) = x 0 (7b) x ( i + 1) = Ax ( i ) + Bu ( i ) i ∈ I [0 , N − 1] (7c) y ( i ) = Cx ( i ) + Du ( i ) i ∈ I [0 , N − 1] (7d) ( x ( i ) , u ( i )) ∈ Z i ∈ I [0 , N − 1] (7e) x r (0) = x r (7f) x r ( i + 1) = Ax r ( i ) + Bu r ( i ) i ∈ I [0 , T − 1] (7g) y r ( i ) = Cx r ( i ) + Du r ( i ) i ∈ I [0 , T − 1] (7h) ( x r ( i ) , u r ( i )) ∈ Z c i ∈ I [0 , N − 1] (7i) x ( N ) = x r ( N ) (7j) Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 14 / 27
Optimization Constraints Basic Constraints Basic constraints are valid at all of the scenarios. Velocity : Never be less than zero , and not exceeding the road speed limit: v min ≤ v k ≤ v max k = 0 .. N (8) Acceleration : Determined from the vehicle’s physical condition: a min ≤ a k ≤ a max k = 0 .. N (9) Acceleration Rate : Variations of acceleration (jerking) should remain in a small range to ensure passengers comfort ∆ a min ≤ ∆ a k ≤ ∆ a max k = 0 .. N (10) Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 15 / 27
Optimization Constraints Car Following Scenarios Position constraints are added to the basic constraints d max k = min ( d front i − gap ) t = 0 .. N (11a) d min k = max ( d rear i − gap ) t = 0 .. N (11b) Position Reference d ref k = d min k + d max k (12) 2 Weight distribution in the cost function 1 R = (13a) ( N v + 1) 2 Q = 1 − R (13b) Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 16 / 27
Optimization Constraints Lane-change Scenarios Position constraints in lane change depend on vehicles in both current and target lanes. d max k = min ( d cl front i − gap , d tl front i − gap ) t = 0 .. t trans (14a) d max k = min ( d tl front i − gap ) t = t trans .. N (14b) d min k = max ( d cl rear i − gap , d tl rear i − gap ) t = 0 .. t trans (14c) d max k = min ( d tl rear i − gap ) t = t trans .. N (14d) Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 17 / 27
Driver Model Model Training SHRP2 Naturalistic driving data Study was conducted with 3 , 000 volunteer drivers aged 16 − 98 over 3 years in several locations across the United States. Vehicles used had an unprecedented scale of sensors installed on them. Model Training Imputation is used to increase observations All available values of acceleration are used to create a model for the position, to predict the missing values of position. The newly imputed values for position and acceleration are used to predict the missing values of velocity following the same procedure. As a result, the number of observations increased from 397 to 4231. %75 of data for training, %25 of data for testing Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 18 / 27
Driver Model Evaluation Prediction Truth r2 rms 0.6 0.5 0.25 0.05 R Squared, RMSE Acceleration 0.1 0.00 0.05 −0.05 0 250 500 750 1000 Figure: Performance of model as Test Set Index tested on OOB samples in 10-fold Figure: Raw acceleration predictions, CV from 10 iterations. tested on OOB samples Saina Ramyar, Dr. Abdollah Homaifar (NCAT) A Personalized Highway Driving Assistance System March, 2017 19 / 27
Recommend
More recommend
