We consider the problem of learning good trajectories for manipulation tasks. This is challenging because the criterion defining a good trajectory varies with users, tasks and environments. In this paper, we propose a co-active online learning framework for teaching robots the preferences of its users for object manipulation tasks. The key novelty of our approach lies in the type of feedback expected from the user: the human user does not need to demonstrate optimal trajectories as training data, but merely needs to iteratively provide trajectories that slightly improve over the trajectory currently proposed by the system. We argue that this co-active preference feedback can be more easily elicited from the user than demonstrations of optimal trajectories, which are often challenging and non-intuitive to provide on high degrees of freedom manipulators. Nevertheless, theoretical regret bounds of our algorithm match the asymptotic rates of optimal trajectory algorithms. We demonstrate the generalizability of our algorithm on a variety of grocery checkout tasks, for whom, the preferences were not only influenced by the object being manipulated but also by the surrounding environment.\footnote{For more details and a demonstration video, visit: \url{http://pr.cs.cornell.edu/coactive}}
A redundant manipulator has multiple inverse kinematics solutions per end-effector pose. Accordingly, there can be many trajectories for joints that follow a given endeffector path in the Cartesian space. In this paper, we present a trajectory optimization of a redundant manipulator (TORM) to synthesize a trajectory that follows a given end-effector path accurately, while achieving smoothness and collisionfree manipulation. Our method holistically incorporates three desired properties into the trajectory optimization process by integrating the Jacobian-based inverse kinematics solving method a…
Fast and precise motion control is important for industrial robots in manufacturing applications. However, some collaborative robots sacrifice precision for safety, particular for high motion speed. The performance degradation is caused by the inability of the joint servo controller to address the uncertain nonlinear dynamics of the robot arm, e.g., due to joint flexibility. We consider two approaches to improve the trajectory tracking performance through feedforward compensation. The first approach uses iterative learning control, with the gradient-based iterative update generated from the ro…
We present a cost-efficient and versatile method to map an unknown 3D freeform surface using only sparse measurements while the end-effector of a robotic manipulator moves along the surface. The geometry is locally approximated by a plane, which is defined by measured points on the surface. The method relies on linear Kalman filters, estimating the height of each point on a 2D grid. Therefore, the approximation covariance for each grid point is determined using a radial basis function to consider the measured point positions. We propose different update strategies for the grid points exploitin…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；Northeastern University（东北大学）
Robot social navigation is influenced by human preferences and environment-specific scenarios such as elevators and doors, thus necessitating end-user adaptability. State-of-the-art approaches to social navigation fall into two categories: model-based social constraints and learning-based approaches. While effective, these approaches have fundamental limitations -- model-based approaches require constraint and parameter tuning to adapt to preferences and new scenarios, while learning-based approaches require reward functions, significant training data, and are hard to adapt to new social scena…
We consider the problem of learning preferences over trajectories for mobile manipulators such as personal robots and assembly line robots. The preferences we learn are more intricate than simple geometric constraints on trajectories; they are rather governed by the surrounding context of various objects and human interactions in the environment. We propose a coactive online learning framework for teaching preferences in contextually rich environments. The key novelty of our approach lies in the type of feedback expected from the user: the human user does not need to demonstrate optimal trajec…
Optimal control is often used in robotics for planning a trajectory to achieve some desired behavior, as expressed by the cost function. Most works in optimal control focus on finding a single optimal trajectory, which is then typically tracked by another controller. In this work, we instead consider trajectory distribution as the solution of an optimal control problem, resulting in better tracking performance and a more stable controller. A Gaussian distribution is first obtained from an iterative Linear Quadratic Regulator (iLQR) solver. A short horizon Model Predictive Control (MPC) is then…
Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from human teachers can be collected either passively or actively in a variety of forms: passive data sources include demonstrations, (e.g., kinesthetic guidance), whereas preferences (e.g., comparative rankings) are actively elicited. Prior research has independently applied reward learning to these different data sources. However, there exist many domains where …
Configuration space (C-space) has played a central role in collision-free motion planning, particularly for robot manipulators. While it is possible to check for collisions at a point using standard algorithms, to date no practical method exists for computing collision-free C-space regions with rigorous certificates due to the complexities of mapping task-space obstacles through the kinematics. In this work, we present the first to our knowledge method for generating such regions and certificates through convex optimization. Our method, called C-Iris (C-space Iterative Regional Inflation by Se…
The Hong Kong Polytechnic University（香港理工大学）；Soochow University（苏州大学）
A cable-driven soft-bodied robot with redundancy can conduct the trajectory tracking task and in the meanwhile fulfill some extra constraints, such as tracking through an end-effector in designated orientation, or get rid of the evitable manipulator-obstacle collision. Those constraints require rational planning of the robot motion. In this work, we derived the compressible curvature kinematics of a cable-driven soft robot which takes the compressible soft segment into account. The motion planning of the soft robot for a trajectory tracking task in constrained conditions, including fixed orien…
IIIT Hyderabad（国际信息技术研究所海得拉巴分校）；University of Tartu（塔尔图大学）
Joint space trajectory optimization under end-effector task constraints leads to a challenging non-convex problem. Thus, a real-time adaptation of prior computed trajectories to perturbation in task constraints often becomes intractable. Existing works use the so-called warm-starting of trajectory optimization to improve computational performance. We present a fundamentally different approach that relies on deriving analytical gradients of the optimal solution with respect to the task constraint parameters. This gradient map characterizes the direction in which the prior computed joint traject…
Optimizing lower-body exoskeleton walking gaits for user comfort requires understanding users' preferences over a high-dimensional gait parameter space. However, existing preference-based learning methods have only explored low-dimensional domains due to computational limitations. To learn user preferences in high dimensions, this work presents LineCoSpar, a human-in-the-loop preference-based framework that enables optimization over many parameters by iteratively exploring one-dimensional subspaces. Additionally, this work identifies gait attributes that characterize broader preferences across…
Laboratoire des Sciences de l’Information et des Sytèmes（信息与系统科学实验室）
To ease the development of robot learning in industry, two conditions need to be fulfilled. Manipulators must be able to learn high accuracy and precision tasks while being safe for workers in the factory. In this paper, we extend previously submitted work which consists in rapid learning of local high accuracy behaviors. By exploration and regression, linear and quadratic models are learnt for respectively the dynamics and cost function. Iterative Linear Quadratic Gaussian Regulator combined with cost quadratic regression can converge rapidly in the final stages towards high accuracy behavior…
