TDR-OBCA: A Reliable Planner for Autonomous Driving in Free-Space Environment

Abstract

This paper presents an optimization-based collision avoidance trajectory generation method for autonomous driving in free-space environments, with enhanced robustness, driving comfort and efficiency. Starting from the hybrid optimization-based framework, we introduces two warm start methods, temporal and dual variable warm starts, to improve the efficiency. We also reformulates the problem to improve the robustness and efficiency. We name this new algorithm TDR-OBCA. With these changes, compared with original hybrid optimization we achieve a 96.67% failure rate decrease with respect to initial conditions, 13.53% increase in driving comforts and 3.33% to 44.82% increase in planner efficiency as obstacles number scales. We validate our results in hundreds of simulation scenarios and hundreds of hours of public road tests in both U.S. and China. Our source code is available at https://github.com/ApolloAuto/apollo.

A guaranteed collision‐free trajectory planning method for autonomous parking

“…As a result, the warm start problem takes an average of 13ms to solve, and the NLP problem takes 1.39s to solve. Overall, TDR-OBCA achieves an 11.5% efficiency improvement over H-OBCA in the parallel parking scenarios, and the time consumption of H-OBCA and TDR-OBCA are similar to that in [8] [23].…”

“…And ( 16) is equivalent to (15). Note that (11h) is a second order cone constraint, and to simplify the warm start problem, [8] put the constraint A T m λ m,k 2 ≤ 1 into objective function. Then the warm start problem is given by min…”

“…Although this approach converts the original non-convex and nonlinear optimization problem to a convex and nonlinear one, it is unacceptable to make the dimension of the problem increase dramatically. Recent improvements based on OBCA [7] is dual warm starts with Reformulated OBCA (TDR-OBCA), and have shown promising results in real world implementation [8]. However, the computational time is still far from satisfactory.…”

Motion planning for efficient and safe module transportation in modular integrated construction

“…Paths calculated by the above algorithms usually have cusps and are not smooth, and many numerical optimization algorithms (e.g., He et al., 2020; Kogan et al., 2006) were developed to solve these problems. Besides, algorithms in the four groups can be combined to achieve better performance.…”

“…For example, He et al. (2020) developed a numerical optimization method named Temporal and DualWarm Starts with Reformulated Optimization‐based Collisio Avoidance (TDR‐OBCA) that utilizes Hybrid A* to generate an initialization state.…”