Serial-link manipulators are required to execute trajectories that enable a robot end-effector or a tool to track a Cartesian path. Practical applications may not require constraining all six degrees of freedom (position and orientation) of the tool resulting in semi-constrained paths. Semi-constrained paths allow improved success rates and better quality trajectories as the robot has more freedom to meet the kinematic and dynamic constraints. Additionally, robotic applications will need to use multiple tool center points (TCPs) on the tool to generate feasible paths for the robot. We present an iterative graph construction method to find trajectories for semi-constrained Cartesian paths that also use multiple TCPs. Our graph-based method finds multiple inverse kinematic solutions for possible Cartesian poses that the robot can take and connects them to build a graph. The algorithm uses cues from the Cartesian space to prioritize poses that produce a better quality solution. A biasing scheme is also developed to selectively sample the starting Cartesian poses from available choices. Our method finds near-optimal solutions with significantly fewer nodes and edges in the graph. The algorithm’s performance results on complex industrial test cases are provided. Note to Practitioners—Industrial applications permit the relaxation of one or more degrees of freedom of the tool while following the Cartesian paths. The relaxation of constraints is introduced by defining tolerances between the tool and the workpiece. Multiple TCPs have to be employed for many tasks to use different surfaces of the tool. In this paper, we present a planning algorithm for semi-constrained Cartesian paths that can incorporate the use of multiple TCPs. The user can define discrete TCPs over the tool contact points or surfaces. The tolerances can be easily defined as angular limits on tool orientation along the Cartesian path. Our planning algorithm can work with others via point constraints in Cartesian space or joint space of the robot. Practitioners from the industry can use the method presented in this paper to develop automated robotic cells that do cutting, sanding, polishing, welding, painting, composite layup, additive manufacturing, and several other common applications.

Mobile manipulators are being deployed for transporting parts between machines and work stations in warehouses and shop floors. To increase the efficiency of operations, these mobile manipulators are required to complete the tasks as fast as possible. Picking up parts with the manipulator while the mobile base is moving decreases the time required to complete the transportation task and increases the efficiency of operations. However, motions of the manipulator on a moving platform can be risky, and hence, it is desired that the manipulator starts and ends its motions as close as possible to the part being picked up. In this article, we present a bidirectional sampling-based scheme for generating such manipulator trajectories for a given mobile base trajectory for pickup and transportation. Our approach implicitly determines the location of the mobile base where the manipulator motion starts and ends as well as where grasping happens. It also determines which grasping pose to use for picking up the part. Furthermore, we have presented the techniques to reduce the manipulator motion time (span time) and the computation time. Our approach enables us to reduce span time on average by 35% with a$16\times $reduction in the computation time compared to the RRT-based baseline methods.Note to Practitioners—Transportation of objects is a crucial application in industrial and warehouse environments. Conveyor belts and AGVs are typically used for such applications as they provide an efficient mode of transportation of a large number of objects. However, they may not provide the flexibility which mobile manipulators bring in for small-scale operations. The method presented in this article provides a way to increase the efficiency of operation for mobile manipulators for transportation tasks. We attempt to reduce the risks of the manipulator colliding with expensive equipment and moving obstacles by making sure that the manipulator moves only when needed for picking up objects. Moreover, the method can be used to pick up and transport a variety of parts in different ways using a two-fingered gripper. The method can also easily incorporate different types of grippers and mobile platforms.

Multi-arm mobile manipulators can be represented as a combination of multiple robotic agents from the perspective of task-assignment and motion planning. Depending upon the task, agents might collaborate or work independently. Integrating motion planning with task-agent assignment is a computationally slow process as infeasible assignments can only be detected through expensive motion planning queries. We present three speed-up techniques for addressing this problem-(1) spatial constraint checking using conservative surrogates for motion planners, (2) instantiating symbolic conditions for pruning infeasible assignments, and (3) efficiently caching and reusing previously generated motion plans. We show that the developed method is useful for real-world operations that require complex interaction and coordination among high-DOF robotic agents.

Determining a feasible path for nonholonomic mobile manipulators operating in congested environments is challenging. Sampling-based methods, especially bi-directional tree search-based approaches, are amongst the most promising candidates for quickly finding feasible paths. However, sampling uniformly when using these methods may result in high computation time. This paper introduces two techniques to accelerate the motion planning of such robots. The first one is coordinated focusing of samples for the manipulator and the mobile base based on the information from robot surroundings. The second one is a heuristic for making connections between the two search trees, which is challenging owing to the nonholonomic constraints on the mobile base. Incorporating these two techniques into the bi-directional RRT framework results in about 5x faster and 10x more successful computation of paths as compared to the baseline method.

We pose the problem of path-constrained trajectory generation for the synchronous motion of multi-robot systems as a non-linear optimization problem. Our method determines appropriate parametric representation for the configuration variables, generates an approximate solution as a starting point for the optimization method, and uses successive refinement techniques to solve the problem in a computationally efficient manner. We have demonstrated the effectiveness of the proposed method on challenging simulation and physical experiments with high degrees of freedom robotic systems.

To minimize the operation time, mobile manipulators need to pick-up parts while the mobile base and the gripper are moving. The gripper speed needs to be selected to ensure that the pick-up operation does not fail due to uncertainties in part pose estimation. This, in turn, affects the mobile base trajectory. This paper presents an active learning based approach to construct a meta-model to estimate the probability of successful part pick-up for a given level of uncertainty in the part pose estimate. Using this model, we present an optimization-based framework to generate time-optimal trajectories that satisfy the given level of success probability threshold for picking-up the part.

We present a context-dependent bi-directional tree-search framework for point-to-point path planning for manipulators. Conceptually, our framework is composed of six modules: tree selection, focus selection, node selection, target selection, extend selection and connection type selection. Each module consists of a set of interchangeable strategies. By exploiting synergistic interaction between these strategies and selecting appropriate strategies based the contextual cues from the search state, we show an instance of our framework that computes high-quality solutions in a variety of complex scenarios with a low failure rate. We also show that some popular path planning methods in the literature can be easily represented in our framework. We compare our approach with these popular methods in a diverse set of test scenarios. We report a 15-fold reduction in failure rate coupled with at least a 26% drop in solution suboptimality when compared to the best of the alternative methods.