STEAP: simultaneous trajectory estimation and planning
STEAP: simultaneous trajectory estimation and planning
复制标题
DOI：
10.1007/s10514-018-9770-1
复制
发表时间：
2018-07
影响因子：
3.5
通讯作者：
Mustafa Mukadam;Jing Dong;F. Dellaert;Byron Boots
中科院分区：
文献类型：
--
作者：
Mustafa Mukadam;Jing Dong;F. Dellaert;Byron Boots
我们提出了一个统一的概率框架，同时轨迹估计和规划。估计和规划问题通常被单独考虑，然而，在我们的框架内，我们表明，同时解决它们可以更准确和有效。其关键思想是在每个时间步计算从开始到目标的完整连续时间轨迹。当机器人遍历轨迹时，轨迹的历史部分表示估计问题的解决方案，并且轨迹的未来部分表示规划问题的解决方案。最近的概率推理方法的连续时间定位和映射和连续时间的运动规划的基础上，我们解决了联合问题，通过迭代重新计算themaxum后验概率条件下的所有可用的传感器数据和成本信息。我们的方法可以应对高自由度的轨迹空间，由于有限的传感能力，模型不准确性，执行动作的随机效应，不确定性，并可以找到一个解决方案，在实时。我们评估我们的框架经验在模拟和移动的机械手。
We present a unified probabilistic framework for simultaneous trajectory estimation and planning. Estimation and planning problems are usually considered separately, however, within our framework we show that solving them simultaneously can be more accurate and efficient. The key idea is to compute the full continuous-time trajectory from start to goal at each time-step. While the robot traverses the trajectory, the history portion of the trajectory signifies the solution to the estimation problem, and the future portion of the trajectory signifies a solution to the planning problem. Building on recent probabilistic inference approaches to continuous-time localization and mapping and continuous-time motion planning, we solve the joint problem by iteratively recomputing themaximum a posterioritrajectory conditioned on all available sensor data and cost information. Our approach can contend with high-degree-of-freedom trajectory spaces, uncertainty due to limited sensing capabilities, model inaccuracy, the stochastic effect of executing actions, and can find a solution in real-time. We evaluate our framework empirically in both simulation and on a mobile manipulator.