Learning latent actions to control assistive robots.
Learning latent actions to control assistive robots.
复制标题
DOI：
10.1007/s10514-021-10005-w
复制
发表时间：
2022
影响因子：
3.5
通讯作者：
Sadigh D
中科院分区：
文献类型：
--
作者：
Losey DP;Jeon HJ;Li M;Srinivasan K;Mandlekar A;Garg A;Bohg J;Sadigh D
辅助机器人手臂使残疾人能够独立完成日常任务。这些手臂灵巧而高维；然而，人们必须用来控制机器人的接口是低维的。考虑使用 2 自由度操纵杆远程操作 7 自由度机器人手臂。机器人正在帮你吃晚饭，现在你想切一块豆腐。今天的机器人在操纵杆输入和机器人动作之间采用预定义的映射：在一种模式下，操纵杆控制机器人在 x-y 平面上的运动，在另一种模式下，操纵杆控制机器人的 z-偏航运动，等等。但此映射错过了您尝试执行的任务！理想情况下，一个操纵杆轴应控制机器人刺豆腐的方式，另一个轴应控制不同的切割动作。我们的见解是，通过将机器人的高维动作嵌入到低维且人类可控的潜在动作中，我们可以实现对辅助机器人的直观、用户友好的控制。我们将这个过程分为三个部分。首先，我们探索从离线任务演示中学习潜在动作的模型，并形式化潜在动作应满足的属性。接下来，我们将学习到的潜在动作与自主机器人辅助相结合，帮助用户实现并维持他们的高水平目标。最后，我们学习操纵杆输入和潜在动作之间的个性化对齐模型。我们在四项用户研究中评估了我们的方法，其中非残疾人参与者拿到棉花糖、煮苹果派、切豆腐和组装甜点。然后，我们对两名每天使用辅助设备的残疾成年人测试我们的方法。
Assistive robot arms enable people with disabilities to conduct everyday tasks on their own. These arms are dexterous and high-dimensional; however, the interfaces people must use to control their robots are low-dimensional. Consider teleoperating a 7-DoF robot arm with a 2-DoF joystick. The robot is helping you eat dinner, and currently you want to cut a piece of tofu. Today’s robots assume a pre-defined mapping between joystick inputs and robot actions: in one mode the joystick controls the robot’s motion in the x–y plane, in another mode the joystick controls the robot’s z–yaw motion, and so on. But this mapping misses out on the task you are trying to perform! Ideally, one joystick axis should control how the robot stabs the tofu, and the other axis should control different cutting motions. Our insight is that we can achieve intuitive, user-friendly control of assistive robots by embedding the robot’s high-dimensional actions into low-dimensional and human-controllable latent actions. We divide this process into three parts. First, we explore models for learning latent actions from offline task demonstrations, and formalize the properties that latent actions should satisfy. Next, we combine learned latent actions with autonomous robot assistance to help the user reach and maintain their high-level goals. Finally, we learn a personalized alignment model between joystick inputs and latent actions. We evaluate our resulting approach in four user studies where non-disabled participants reach marshmallows, cook apple pie, cut tofu, and assemble dessert. We then test our approach with two disabled adults who leverage assistive devices on a daily basis.
登录
查看更多内容
DOI：
10.1109/hri.2016.7451731
发表时间：
2016-03
期刊：
Proceedings of the ... ACM SIGCHI. ACM Conference on Human-Robot Interaction
影响因子：
--
作者：
Herlant LV;Holladay RM;Srinivasa SS
通讯作者：
Srinivasa SS
DOI：
10.1146/annurev-control-061417-041727
发表时间：
2018-05
期刊：
Annual review of control, robotics, and autonomous systems
影响因子：
--
作者：
Argall BD
通讯作者：
Argall BD
影响因子：
5.1
作者：
Jain, Siddarth;Argall, Brenna
通讯作者：
Argall, Brenna
影响因子：
9.2
作者：
Broad, Alexander;Abraham, Ian;Argall, Brenna
通讯作者：
Argall, Brenna
影响因子：
5.7
作者：
Carlson, Tom;Millan, Jose del R.
通讯作者：
Millan, Jose del R.