We provide software algorithms for cooperative automated driving, specifically applied to last mile solutions. A people mover (Figure 1, courtesy of EASYMILE) or automated shuttle bus, is an example last mile transportation solution to bring people from a transportation hub (e.g., railway station) to their final destination. These solutions are typically interesting for transporting people over small distances on university campuses, airports, private industrial areas, ports or urban areas.
Where automated shuttle buses react to their sensed surroundings, cooperative automated buses can share their intentions and plan coordinated actions. The full potential of automated driving can only be reached by combining cooperative driving and automated driving to improve vehicle and traffic efficiency, safety and comfort. Complex urban situations like intersections (see Figure 2) and interactions with Vulnerable Road Users (VRUs, like pedestrians and bicyclists) can be eased by roadside-to-vehicle communication (‘V2I communication’), broadening the perception horizon of the automated vehicles. Simultaneously, this will also improve safety of VRUs.
The technology aims at (control) algorithms to influence the individual vehicle behavior (either through advisory or automated actions), so as to optimize the collective behavior with respect to road throughput, fuel efficiency, and/or safety.
The technology comprises software algorithms for execution of common traffic scenarios (platooning, merging, crossing, etc.), automatically and cooperatively.
In order to obtain a generic solution, scenarios are decomposed into maneuvers as depicted in figure 3. The maneuvers are executed by a set of high-level controllers, a.k.a. agents. In order to execute a specific scenario, a well-defined interaction protocol is required.
The interaction protocol is characterized by 1) a sequence of maneuvers to execute a scenario, 2) a corresponding event sequence to trigger specific maneuvers, implemented by wireless communications to inform vehicles that are engaged in the scenario execution. Figure 4 shows the implementation of the merging scenario and corresponding interaction protocol.
Two scenarios have been developed, implemented and successfully demonstrated during the Grand Cooperative Driving Challenge (GCDC) 2016.
Autonomous vehicles for last mile transporation at
There is a growing demand for last mile solutions.