Autonomous Driving on Curvy Roads Without Reliance on Frenet Frame: A Cartesian-Based Trajectory Planning Method

Abstract

Curvy roads are a particular type of urban road scenario, wherein the curvature of the road centerline changes drastically. This paper is focused on the trajectory planning task for autonomous driving on a curvy road. The prevalent on-road trajectory planners in the Frenet frame cannot impose accurate restrictions on the trajectory curvature, thus easily making the resultant trajectories beyond the ego vehicle's kinematic capability. Regarding planning in the Cartesian frame, selection-based methods suffer from the curse of dimensionality. By contrast, optimization-based methods in the Cartesian frame are more flexible to find optima in the continuous solution space, but the new challenges are how to tackle the intractable collision-avoidance constraints and nonconvex kinematic constraints. An iterative computation framework is proposed to accumulatively handle the complex constraints. Concretely, an intermediate problem is solved in each iteration, which contains linear and tractably scaled collision-avoidance constraints and softened kinematic constraints. Compared with the existing optimization-based planners, our proposal is less sensitive to the initial guess especially when it is not kinematically feasible. The efficiency of the proposed planner is validated by both simulations and realworld experiments. Source codes of this work are available at https://github.com/libai1943/CartesianPlanner.

Mixed-Integer and Conditional Trajectory Planning for an Autonomous Mining Truck in Loading/Dumping Scenarios: A Global Optimization Approach

“…The workspace is also cluttered by small surface stones, which render multiple homotopy classes. Ideally, a planned parking trajectory should have an optimal homotopy class, otherwise the traverse efficiency is degraded [16,17].…”

Search-based task and motion planning for hybrid systems: Agile autonomous vehicles

“…On the other hand, the vehicle dynamic model in the Cartesian coordinate system is still used for motion primitive generation. Therefore, we effectively avoid problems of Frenet frame like shown by Li et al (2022). Efficient transformations between Frenet and Cartesian frames are necessary as they are used frequently (for every explored node) in each planning step.…”

“…For validating the advantage of using multiple modes (i.e., drifting) we benchmark our approach to other state-ofthe-art approaches that do not use drifting mode but can still drive full circle autonomously. Due to the low friction coefficient of the dirt road, we found other approaches like Liniger et al (2015) and Li et al (2022) difficult to adapt for these conditions and achieve the full circuit driving. After extensive unsuccessful trials, we used our planner with disabled drifting mode.…”

Sharing Traffic Priorities via Cyber–Physical–Social Intelligence: A Lane-Free Autonomous Intersection Management Method in Metaverse

“…Numerical Solution to the OCP: The aforementioned elements form an OCP, the solution to which represents the cooperative trajectories at the traverse stage. Solving this nonconvex OCP analytically is impossible, thus, it is solved numerically instead [66], [67], [68]. Concretely, the OCP is discretized along the time horizon to formulate an NLP, which is thereafter solved by a gradient-based NLP solver.…”