scholarly journals Human-Machine Cooperative Trajectory Planning for Semi-Autonomous Driving Based on the Understanding of Behavioral Semantics

Electronics ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 946
Author(s):  
Bohan Jiang ◽  
Xiaohui Li ◽  
Yujun Zeng ◽  
Daxue Liu
Keyword(s):  
Decision Making ◽  
Trajectory Planning ◽  
Autonomous Driving ◽  
Planning Problem ◽  
Decision Level ◽  
Planning Approach ◽  
Decision Making Problem ◽  
Generation Level ◽  
High Level ◽  
Real Vehicle

This paper presents a novel cooperative trajectory planning approach for semi-autonomous driving. The machine interacts with the driver at the decision level and the trajectory generation level. To minimize conflicts between the machine and the human, the trajectory planning problem is decomposed into a high-level behavior decision-making problem and a low-level trajectory planning problem. The approach infers the driver’s behavioral semantics according to the driving context and the driver’s input. The trajectories are generated based on the behavioral semantics and driver’s input. The feasibility of the proposed approach is validated by real vehicle experiments. The results prove that the proposed human–machine cooperative trajectory planning approach can successfully help the driver to avoid collisions while respecting the driver’s behavior.

Transfer Reinforcement Learning for Autonomous Driving

2021 ◽  
Vol 31 (3) ◽  
pp. 1-26
Author(s):  
Aravind Balakrishnan ◽  
Jaeyoung Lee ◽  
Ashish Gaurav ◽  
Krzysztof Czarnecki ◽  
Sean Sedwards
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Transfer Problem ◽  
Autonomous Driving ◽  
High Fidelity ◽  
Rule Based ◽  
High Level ◽  
Real Vehicle

Reinforcement learning (RL) is an attractive way to implement high-level decision-making policies for autonomous driving, but learning directly from a real vehicle or a high-fidelity simulator is variously infeasible. We therefore consider the problem of transfer reinforcement learning and study how a policy learned in a simple environment using WiseMove can be transferred to our high-fidelity simulator, W ise M ove . WiseMove is a framework to study safety and other aspects of RL for autonomous driving. W ise M ove accurately reproduces the dynamics and software stack of our real vehicle. We find that the accurately modelled perception errors in W ise M ove contribute the most to the transfer problem. These errors, when even naively modelled in WiseMove , provide an RL policy that performs better in W ise M ove than a hand-crafted rule-based policy. Applying domain randomization to the environment in WiseMove yields an even better policy. The final RL policy reduces the failures due to perception errors from 10% to 2.75%. We also observe that the RL policy has significantly less reliance on velocity compared to the rule-based policy, having learned that its measurement is unreliable.

A Comparison of Trajectory Planning and Control Frameworks for Cooperative Autonomous Driving

2021 ◽  
Vol 143 (7) ◽  
Author(s):  
Icaro Bezerra Viana ◽  
Husain Kanchwala ◽  
Kenan Ahiska ◽  
Nabil Aouf
Keyword(s):  
Trajectory Planning ◽  
Cooperative Behavior ◽  
Autonomous Driving ◽  
General Idea ◽  
Mixed Integer ◽  
Quadratic Program ◽  
Change Scenario ◽  
Planning Problem ◽  
Lane Change ◽  
Double Lane Change

Abstract This work considers the cooperative trajectory-planning problem along a double lane change scenario for autonomous driving. In this paper, we develop two frameworks to solve this problem based on distributed model predictive control (MPC). The first approach solves a single nonlinear MPC problem. The general idea is to introduce a collision cost function in the optimization problem at the planning task to achieve a smooth and bounded collision function, and thus to prevent the need to implement tight hard constraints. The second method uses a hierarchical scheme with two main units: a trajectory-planning layer based on mixed-integer quadratic program (MIQP) computes an on-line collision-free trajectory using simplified motion dynamics, and a tracking controller unit to follow the trajectory from the higher level using the nonlinear vehicle model. Connected and automated vehicles (CAVs) sharing their planned trajectories lay the foundation of the cooperative behavior. In the tests and evaluation of the proposed methodologies, matlab-carsim cosimulation is utilized. carsim provides the high-fidelity model for the multibody vehicle dynamics. matlab-carsim conjoint simulation experiments compare both approaches for a cooperative double lane change maneuver of two vehicles moving along a one-way three-lane road with obstacles.

Multi-Car Convex Feasible Set Algorithm in Trajectory Planning

2020 ◽  
Author(s):  
Jing Huang ◽  
Changliu Liu
Keyword(s):  
Convex Optimization ◽  
Quadratic Programming ◽  
Real Time ◽  
Trajectory Planning ◽  
Autonomous Driving ◽  
Curse Of Dimensionality ◽  
Planning Problem ◽  
Feasible Set ◽  
Planning Algorithm ◽  
Vehicle Trajectory

Abstract Trajectory planning is an essential module for autonomous driving. To deal with multi-vehicle interactions, existing methods follow the prediction-then-plan approaches which first predict the trajectories of others then plan the trajectory for the ego vehicle given the predictions. However, since the true trajectories of others may deviate from the predictions, frequent re-planning for the ego vehicle is needed, which may cause many issues such as instability or deadlock. These issues can be overcome if all vehicles can form a consensus by solving the same multi-vehicle trajectory planning problem. Then the major challenge is how to efficiently solve the multi-vehicle trajectory planning problem in real time under the curse of dimensionality. We introduce a novel planner for multi-vehicle trajectory planning based on the convex feasible set (CFS) algorithm. The planning problem is formulated as a non-convex optimization. A novel convexification method to obtain the maximal convex feasible set is proposed, which transforms the problem into a quadratic programming. Simulations in multiple typical on-road driving situations are conducted to demonstrate the effectiveness of the proposed planning algorithm in terms of completeness and optimality.

scholarly journals Minimum-jerk trajectory planning pertaining to a translational 3-degree-of-freedom parallel manipulator through piecewise quintic polynomials interpolation

2020 ◽  
Vol 12 (3) ◽  
pp. 168781402091366 ◽  
Author(s):  
Song Lu ◽  
Bingxiao Ding ◽  
Yangmin Li
Keyword(s):  
Trajectory Planning ◽  
Virtual Work ◽  
Angular Position ◽  
Programming Algorithm ◽  
Planning Problem ◽  
Typical Application ◽  
Parallel Kinematic Manipulator ◽  
Minimum Jerk ◽  
Planning Approach ◽  
Parallel Kinematic

This article aims to present a minimum-jerk trajectory planning approach to address the smooth trajectory generation problem of 3-prismatic-universal-universal translational parallel kinematic manipulator. First, comprehensive kinematics and dynamics characteristics of this 3-prismatic-universal-universal parallel kinematic manipulator are analyzed by virtue of the accepted link Jacobian matrices and proverbial virtual work principle. To satisfy indispensable continuity and smoothness requirements, the discretized piecewise quintic polynomials are employed to interpolate the sequence of joints’ angular position knots which are transformed from these predefined via-points in Cartesian space. Furthermore, the trajectory planning problem is directly converted into a constrained nonlinear multi-variables optimization problem of which objective function is to minimize the maximum of the joints’ angular jerk throughout the whole trajectory. Finally, two typical application simulations using the reliable sequential quadratic programming algorithm demonstrate that this proposed minimum-jerk trajectory planning approach is of explicit feasibility and appreciable effectiveness.

scholarly journals Psychophysiology and high-performance cognition - a brief review of the literature

2015 ◽  
Author(s):  
Benjamin Cowley
Keyword(s):  
Decision Making ◽  
Executive Control ◽  
High Performance ◽  
Time Pressure ◽  
Mental Workload ◽  
Knowledge Work ◽  
Review Of The Literature ◽  
Cognitive States ◽  
Decision Making Problem ◽  
High Level

The psychophysiological method can be used to detect some simple cognitive states such as arousal, attentiveness, or mental workload. This approach can be especially interesting when cognition has some productive purpose, as in knowledge work, and tends to be related to human-computer interaction (HCI). However more interesting for applied purposes are acts of coordinated high-level cognition. High- level (or higher-order) cognition (HLC) is typically associated with decision making, problem solving, and executive control of cognition and action. Further, an intuitive approach for assessing whether someone is engaged in HLC is to measure their performance of a known task. Given this, it is reasonable to define high-performance cognition (HPC) as HLC under some performance restriction, such as real-time pressure or expert skill level. Such states are also interesting for HCI in work, and their detection represents an ambitious aim for using the psychophysiological method. We report a brief review of the literature on the topic.

scholarly journals OPTIMAL ALTERNATIVE SELECTION MODELS IN A MULTI-STAGE DECISION-MAKING PROCESS

2019 ◽  
Vol 6 ◽  
pp. 43-50
Author(s):  
Oksana Mulesa ◽  
Vitaliy Snytyuk ◽  
Ivan Myronyuk
Keyword(s):  
Decision Making ◽  
Effective Alternative ◽  
Management Decision ◽  
Decision Making Process ◽  
Multi Stage ◽  
Decision Making Problem ◽  
Management Decision Making ◽  
The Face ◽  
Decision Making Models ◽  
High Level

Management decision-making tasks are usually characterized by a high level of uncertainty. When solving this class of problems, it is necessary to take into account the environmental conditions for the implementation of the decisions made and the consequences that may arise in this case. The decision-making task in the face of uncertainty can be represented in the form of a “game with nature”, in which the optimal player strategy is sought. A two-stage decision-making process is considered, in which at each stage the decision-making problem is solved in conditions of risk. The case is supposed in which, after making a decision at the first stage, choosing an effective alternative and the onset of a certain state of nature, it is necessary to solve the decision-making problem of the second stage. Decision-making models based on well-known decision models of the “game with nature” are proposed. The developed models allow in the process of choosing an effective alternative to the first stage to assess the possible consequences of such a choice, taking into account the expectations of the decision maker. In the course of experimental verification, it is shown that the developed decision-making models can be used to solve such multi-stage problems, the phased solution of which is incorrect. This may occur due to the fact that some of their stages are associated with certain losses, and others – with profit. In such situations, it is advisable to consider the problem as a whole and at each stage, take into account all available information as much as possible.

Sign in / Sign up

Export Citation Format

Share Document