基于混合遗传算法的工业机器人最优轨迹规划

Optimal trajectory planning for industrial robot based on hybrid genetic algorithm

为兼顾工业机器人工作效率与轨迹的平稳性,提出一种基于混合遗传算法的二次轨迹规划方案。通过最优时间轨迹规划得到最小执行时间,在最小执行时间内进行最优冲击轨迹规划,进而规划出一条既高效又平滑的运动轨迹。采用五次均匀B样条在关节空间进行快速插值,不仅保证了各关节速度和加速度连续性还保证了各关节冲击的连续性。连续平滑的冲击可以减少机械振动,延长机器人的工作寿命。选用PUMA560为对象进行仿真与实验,结果表明,该方案可以获得比较理想的机器人运动轨迹,所提出的混合遗传算法能有效提高全局寻优的性能和算法运行的稳定性。

In order to improve industrial robot＇s productivity and get a smooth trajectory, a new method for quadratic trajectory planning based on hybrid genetic algorithm is presented. Minimum execution time is obtained by using time-optimal trajectory planning, then an efficient and smooth trajectory is generated in this minimum execution time by using jerk-optimal trajectory planning. Fifth-order uniform B-splines are used to interpolate a sequence of joint variables and the velocity, acceleration and jerk of each joint trajectorys are continuous. With continuous and smooth jerk, mechanical resonance is reduced and the life span of industrial robot is extended. The method is applied to PUMA560, the result of simulation and experimentation shows that the method can provide ideal trajectory and the hybrid genetic algorithm is more efficient and stable.