Much as Hyundai did yesterday, Kia has announced an electrification roadmap at its 2022 Investor Day, promising to have 14 fully electric models by 2027 and sales of 1.2 million EVs by 2030. It also revealed that its EV9 SUV, unveiled in concept form last November at the LA Auto Show, will be the first to use autonomous driving tech it calls "Automode." Kia's roadmap builds on its "Plan S" development strategy announced early in 2021 that included new branding and a plan to introduce of seven EVs by 2027. Now, the company plans to double that with 14 BEV (battery electric vehicle) models available by 2027 and total EV sales of 1.2 million by 2030. It also projects to sell 4 million vehicles annually by 2030, so EVs would make up just over a quarter of that -- while automakers like Mercedes-Benz plan to only sell BEVs by 2030. The strategy is still ambitious, as it's starting with 160,000 BEV sales this year and plans to ramp that up by five times to 807,000 units in 2026 and 1.2 million by 2030.

We investigate the possibilities, challenges, and limitations that arise from the use of behavior trees in the context of the automatic modular design of collective behaviors in swarm robotics. To do so, we introduce Maple, an automatic design method that combines predefined modules—low-level behaviors and conditions—into a behavior tree that encodes the individual behavior of each robot of the swarm. We present three empirical studies based on two missions: aggregation and Foraging. To explore the strengths and weaknesses of adopting behavior trees as a control architecture, we compare Maple with Chocolate, a previously proposed automatic design method that uses probabilistic finite state machines instead. In the first study, we assess Maple’s ability to produce control software that crosses the reality gap satisfactorily. In the second study, we investigate Maple’s performance as a function of the design budget, that is, the maximum number of simulation runs that the design process is allowed to perform. In the third study, we explore a number of possible variants of Maple that differ in the constraints imposed on the structure of the behavior trees generated. The results of the three studies indicate that, in the context of swarm robotics, behavior trees might be appealing but in many settings do not produce better solutions than finite state machines.