Driving strategy in dynamic environment is crucial to the automated vehicle safety. In extremely emergency scenarios with unavoidable collisions, especially those with complex impact patterns, the potential crash risk should be well considered. This paper proposes a crash mitigation algorithm for unavoidable collisions, which directly embeds a generalized crash severity index model to vehicle-to-vehicle collisions of multiple impact patterns. The idea is that during the short time before a collision, the vehicle will actively adapt its position and poses to minimize the potential crash severity level after the collision. To this end, the generalized crash severity index (CSI) model is introduced to estimate the potential crash severity of all sample paths, from which a crash-severityoptimal trajectory is obtained. To improve the inferring time efficiency of the planning module, a neural network is constructed and deployed to approximate the nonlinear severity model. The proposed algorithm is first validated through simulations of unavoidable collision scenarios, Vehicle Crash Mitigation Considering CSI model including entry ramp merging, intersection crossing and downhill/uphill crossing. Then for the intersection crossing scenario, the algorithm is deployed to a real car and validated through digital-twin experiments. Results show that by combining the braking and steering interventions for better crash severity reduction, the proposed strategy can achieve better mitigation effects than commonly-used collision-avoidance strategies. This reveals that a new mindset of comprehensive safety strategy should not focus only on collision avoidance, but also the last resort of crash mitigation if collision is unavoidable. Our work may contribute as a promising solution to the safety problem in emergency scenarios.

No abstract

<div>Motion planning in dynamic environment is crucial to the automated driving safety. In extremely emergency scenarios with unavoidable collisions, especially those with complex impact patterns, the potential crash risk should be well considered in motion planning. This paper proposes a motion planning algorithm for unavoidable collisions, which directly embeds a generalized crash severity index model to vehicle-to-vehicle collisions of multiple impact patterns. Firstly, the clothoid curve is used to sample the vehicle trajectory before collision, and a two-degree-of-freedom model is adopted to predict the vehicle poses corresponding to each sample path. Then, the crash severity index model is to estimate the potential crash severity of all sample paths. To improve the inferring time efficiency, a neural network is constructed and deployed to approximate the nonlinear severity model. Finally, the crash-severity-optimal trajectory is tracked through model predictive control method. Results show that by combining the braking and steering interventions for better crash severity reduction, the proposed strategy can achieve better mitigation effects than commonly-used collision-avoidance strategies. The deployment of real car experiment and sensitivity analysis demonstrate that the planning algorithm can guarantee </div>real-time and reliably safe performances.

<p>Driving strategy in dynamic environment is crucial to the automated vehicle safety. In extremely emergency scenarios with unavoidable collision (UC), especially those with complex impact patterns, the potential crash risk should be well considered. This paper proposes a crash mitigation (CM) algorithm for UCs, which directly embeds a generalized crash severity index (CSI) model to vehicle-to-vehicle collisions of multiple impact patterns. The idea is that during the short time before a collision, the vehicle will actively adapt its position and poses to minimize the potential crash severity level after the collision. To this end, the generalized CSI model is introduced to estimate the potential crash severity of all sample paths, from which a crash-severity-optimal trajectory is obtained. To improve the inferring time efficiency of the planning module, a neural network is constructed and deployed to approximate the nonlinear severity model. The proposed algorithm is first validated through simulations of UC scenarios, including entry ramp merging, intersection crossing and downhill/uphill crossing. Then for the intersection crossing scenario, the algorithm is deployed to a real car and validated through digital-twin experiments. Results show that by combining the braking and steering interventions for better crash severity reduction, the proposed strategy can achieve better mitigation effects than commonly-used collision avoidance (CA) strategies. This reveals that a new mindset of comprehensive safety strategy should not focus only on CA, but also the last resort of CM if collision is unavoidable. Our work may contribute as a promising solution to the safety problem in emergency scenarios.</p>

Motion planning in dynamic environment is crucial to the automated driving safety. In extremely emergency scenarios with unavoidable collisions, especially those with complex impact patterns, the potential crash risk should be well considered in motion planning. This paper proposes a motion planning algorithm for unavoidable collisions, which directly embeds a generalized crash severity index model to vehicle-to-vehicle collisions of multiple impact patterns. Firstly, the clothoid curve is used to sample the vehicle trajectory before collision, and a two-degree-of-freedom model is adopted to predict the vehicle poses corresponding to each sample path. Then, the crash severity index model is to estimate the potential crash severity of all sample paths. To improve the inferring time efficiency, a neural network is constructed and deployed to approximate the nonlinear severity model. Finally, the crash-severity-optimal trajectory is tracked through model predictive control method. Results show that by combining the braking and steering interventions for better crash severity reduction, the proposed strategy can achieve better mitigation effects than commonly-used collision-avoidance strategies. The deployment of real car experiment and sensitivity analysis demonstrate that the planning algorithm can guarantee real-time and reliably safe performances.