This paper extends the gap-based navigation technique in Potential Gap by guaranteeing safety for nonholonomic robots for all tiers of the local planner hierarchy, so called Safer Gap. The first tier generates a Bezier-based collision-free path through gaps. A subset of navigable free-space from the robot through a gap, called the keyhole, is defined to be the union of the largest collision-free disc centered on the robot and a trapezoidal region directed through the gap. It is encoded by a shallow neural network zeroing barrier function (ZBF). Nonlinear model predictive control (NMPC), with Keyhole ZBF constraints and output tracking of the Bezier path, synthesizes a safe kinematically-feasible trajectory. Low-level use of the Keyhole ZBF within a point-wise optimization-based safe control synthesis module serves as a final safety layer. Simulation and experimental validation of Safer Gap confirm its collision-free navigation properties.

翻译：摘要：本文通过对势能间隙法的扩展，确保了非完整机器人在局部规划器各层级的安全性，从而提出了一种名为 Safer Gap 的规划方法。其第一层级通过间隙生成基于贝塞尔曲线的无碰撞路径。从机器人穿越间隙的可导航自由空间子集（称为“钥匙孔”）被定义为以机器人为中心的最大无碰撞圆盘与指向间隙的梯形区域之并集。该空间通过一种浅层神经网络零化屏障函数（ZBF）进行编码。结合钥匙孔ZBF约束及对贝塞尔路径的输出跟踪，非线性模型预测控制（NMPC）生成一条安全的运动学可行轨迹。在低层级中，钥匙孔ZBF被集成到基于逐点优化的安全控制合成模块内，作为最终安全层。对Safer Gap的仿真与实验验证确认了其无碰撞导航性能。