An official website of the United States government
The majority of the past research dealing with lane-changing controller design of autonomous vehicles (𝐴𝑉 s) is based on the assumption of full knowledge of the model dynamics of the 𝐴𝑉 and the surrounding vehicles. However, in the real world, this is not a very realistic assumption as accurate dynamic models are difficult to obtain. Also, the dynamic model parameters might change over time due to various factors. Thus, there is a need for a learning-based lane change controller design methodology that can learn the optimal control policy in real time using sensor data. In this paper, we have addressed this need by introducing an optimal learningbased control methodology that can solve the real-time lane-changing problem of 𝐴𝑉 s, where the input-state data of the 𝐴𝑉 is utilized to generate a near-optimal lane-changing controller by approximate/adaptive dynamic programming (ADP) technique. In the case of this type of complex lane-changing maneuver, the lateral dynamics depend on the longitudinal velocity of the vehicle. If the longitudinal velocity is assumed constant, a linear parameter invariant model can be used. However, assuming constant velocity while performing a lane-changing maneuver is not a realistic assumption. This assumption might increase the risk of accidents, especially in the case of lane abortion when the surrounding vehicles are not cooperative. Thus, in this paper, the dynamics of the 𝐴𝑉 are assumed to be a linear parameter-varying system. Thus we have two challenges for the lane-changing controller design: parameter-varying, and unknown dynamics. With the help of both gain scheduling and ADP techniques combined, a learning-based control algorithm that can generate a near-optimal lane-changing controller without having to know the accurate dynamic model of the 𝐴𝑉 is proposed. The inclusion of a gain scheduling approach with ADP makes the controller applicable to non-linear and/or parameter-varying 𝐴𝑉 dynamics. The stability of the learning-based gain scheduling controller has also been rigorously proved. Moreover, a data-driven lane-changing decision-making algorithm is introduced that can make the 𝐴𝑉 perform a lane abortion if safety conditions are violated during a lane change. Finally, the proposed learning-based gain scheduling controller design algorithm and the lane-changing decision-making methodology are numerically validated using MATLAB, SUMO simulations, and the NGSIM dataset.
more »
« less
Compatibility Checking for Autonomous Lane-Changing Assistance Systems
Different types of lane-changing assistance systems are usually developed separately by different automotive makers or suppliers. A lane-changing model can meet its own requirements, but it may be incompatible with another lane-changing model. In this paper, we verify if two lane-changing models are compatible so that the two corresponding vehicles on different lanes can exchange their lanes successfully. We propose a methodology and an algorithm to perform the verification on the combinations of four lane-changing models. Experimental results demonstrate the compatibility (or incompatibility) between the models. The verification results can be utilized during runtime to prevent incompatible vehicles from entering a lane-changing road segment. To the best of our knowledge, this is the first work considering the compatibility issue for lane-changing models.
more »
« less
- Award ID(s):
- 1645578
- PAR ID:
- 10321995
- Date Published:
- Journal Name:
- 25th International Conference on Design Automation and Test in Europe (DATE), 2022
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Flocking control for multi-agent automated vehicles has attracted more research interest recently. However, one significant challenge is that the common use of point-shaped virtual leaders giving uniform navigations is unsuitable for vehicle motions with varying relative positions and orientations on multi-lane roads, particularly on curved sections. Considering the practical movements of multi-agent ground vehicles, this paper proposes a novel type of polyline-shaped leader(s) that aligns with multi-lane roads. Specifically, the polyline-shaped leader is composed of line segments that consider road curvatures, different lanes, and the flocking lattice configuration. Moreover, an artificial flow guidance method is applied to provide the direction of velocity references to ensure vehicles move within their respective lanes during the formed flocking. Simulation results demonstrate that the proposed approach can successfully regulate vehicles to drive in their lanes in coordinated motion, which gives fewer structural deviations on curved roads compared to the case with the point-shaped leader.more » « less
-
Meng, Meng (Ed.)Managed lanes, such as a dedicated lane for connected and automated vehicles (CAVs), can provide not only technological accommodation but also desired market incentives for road users to adopt CAVs in the near future. In this paper, we investigate traffic flow characteristics with two configurations of the managed lane across different market penetration rates and quantify the benefits from the perspectives of lane-level headway distribution, fuel consumption, communication density, and overall network performance. The results highlight the benefits of implementing managed lane strategies for CAVs: (1) A dedicated CAV lane significantly extends the stable region of the speed-flow diagram and yields a greater road capacity. As the result shows, the highest flow rate is 3400 vehicles per hour per lane at 90% market penetration rate with one CAV lane. (2) The concentration of CAVs in one lane results in a narrower headway distribution (with smaller standard deviation) even with partial market penetration. (3) A dedicated CAV lane is also able to eliminate duel-bell-shape distribution that is caused by the heterogeneous traffic flow. (4) A dedicated CAV lane creates a more consistent CAV density, which facilitates communication activity and decreases the probability of packet dropping.more » « less
-
We analyze the effect of a bicycle lane on traffic speeds. Computer vision techniques are used to detect and classify the speed and trajectory of over 9,000 motor-vehicles at an intersection that was part of a pilot demonstration in which a bicycle lane was temporarily implemented. After controlling for direction, hourly traffic flow, and the behavior of the vehicle (i.e., free-flowing or stopped at a red light), we found that the effect of the delineator-protected bicycle lane (marked with traffic cones and plastic delineators) was associated with a 28 % reduction in average maximum speeds and a 21 % decrease in average speeds for vehicles turning right. For those going straight, a smaller reduction of up to 8 % was observed. Traffic moving perpendicular to the bicycle lane experienced no decrease in speeds. Painted-only bike lanes were also associated with a small speed reduction of 11–15 %, but solely for vehicles turning right. These findings suggest an important secondary benefit of bicycle lanes: by having a traffic calming effect, delineated bicycle lanes may decrease the risk and severity of crashes for pedestrians and other road users.more » « less
-
Connected and automated vehicles (CAVs) extend urban traffic control from temporal to spatiotemporal by enabling the control of CAV trajectories. Most of the existing studies on CAV trajectory planning only consider longitudinal behaviors (i.e., in-lane driving), or assume that the lane changing can be done instantaneously. The resultant CAV trajectories are not realistic and cannot be executed at the vehicle level. The aim of this paper is to propose a full trajectory planning model that considers both in-lane driving and lane changing maneuvers. The trajectory generation problem is modeled as an optimization problem and the cost function considers multiple driving features including safety, efficiency, and comfort. Ten features are selected in the cost function to capture both in-lane driving and lane changing behaviors. One major challenge in generating a trajectory that reflects certain driving policies is to balance the weights of different features in the cost function. To address this challenge, it is proposed to optimize the weights of the cost function by imitation learning. Maximum entropy inverse reinforcement learning is applied to obtain the optimal weight for each feature and then CAV trajectories are generated with the learned weights. Experiments using the Next Generation Simulation (NGSIM) dataset show that the generated trajectory is very close to the original trajectory with regard to the Euclidean distance displacement, with a mean average error of less than 1 m. Meanwhile, the generated trajectories can maintain safety gaps with surrounding vehicles and have comparable fuel consumption.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
