Semi-autonomous Intersection Collision Avoidance through Job-shop Scheduling

Abstract

In this paper, we design a supervisor to prevent vehicle collisions at intersections. An intersection is modeled as an area containing multiple conflict points where vehicle paths cross in the future. At every time step, the supervisor determines whether there will be more than one vehicle in the vicinity of a conflict point at the same time. If there is, then an impending collision is detected, and the supervisor overrides the drivers to avoid collision. A major challenge in the design of a supervisor as opposed to an autonomous vehicle controller is to verify whether future collisions will occur based on the current drivers choices. This verification problem is particularly hard due to the large number of vehicles often involved in intersection collision, to the multitude of conflict points, and to the vehicles dynamics. In order to solve the verification problem, we translate the problem to a job-shop scheduling problem that yields equivalent answers. The job-shop scheduling problem can, in turn, be transformed into a mixed-integer linear program when the vehicle dynamics are first-order dynamics, and can thus be solved by using a commercial solver.

Least restrictive and minimally deviating supervisor for Safe semi-autonomous driving at an intersection: An MIQP approach

“…Note that the optimal supervision problem is an instance of the least-restrictive supervision problem, in the sense that any solution to SP * is a solution to SP .However, not all solutions of SP are solutions of SP * . Previous literature [7], [9], [10] mainly considers SP , by converting it to an equivalent scheduling problem. Campos et al [11] proposed to exhaustively enumerate all solutions of SP to find the solution to SP * , which may be computationally costly.…”

“…Reference [9] designs a supervisor which is robust to bounded uncertainties by adding safety margins. Reference [10] leverages job-shop scheduling to develop a supervisor that considers several possible conflict points inside the intersection; however, vehicles are modeled as single integrators which is not realistic in a realworld setting. Campos et al [11] proposed a Pareto-optimal supervisor leading to a minimally deviating formulation by recursively finding the most constrained vehicle, reserving its optimal crossing time, and scheduling the crossing of the other vehicles using the previously scheduled ones as constraints.…”

“…This formulation, extending our previous work on time-optimal coordination of fully autonomous vehicles [14], results in a mixed-integer quadratic program (MIQP) that can be solved using widely available software. Compared to previous approaches [7], [9], [10], the advantage of our formulation is twofold: 1) intersections with complex geometries (crossing, merging and diverging paths) can be handled intuitively, 2) the computational burden can be significantly reduced as we only consider a finite time horizon, and use highly efficient MIQP solvers.…”

Cooperative Intelligence in Roundabout Intersections Using Hierarchical Fuzzy Behavior Calculation of Vehicle Speed Profile

“…Some papers use linear programming algorithms, e.g. [16] uses job-shop scheduling. Centralized V2I coordination that employs Active set method and Interior point method for optimization is used in [17].…”

Abstraction-Based Safety Verification and Control of Cooperative Vehicles at Road Intersections

“…2, it prevents cars 1 and 4 from simultaneously being inside the intersection although their collision is geometrically impossible. More recent methods [15]- [18] handle a more realistic intersection model with multiple conflict areas, such as the shaded areas in Fig. 2, but fixed vehicles' paths.…”