The problem of planning a trajectory for robots starting in an initial state and reaching a final state in a desired interval of time is tackled. We propose an approach based on model predictive control to solve the problem of point-to-point trajectory generation for a given final time. We discuss various choices of models, objective functions, and constraints for generating trajectories to transfer the state of the robot, while respecting physical limitations on the motion as well as fulfilling computational real-time requirements. Extensive simulation results illustrate the use of the approach, and experiments on an industrial robot in a challenging ball-catching task show the effectiveness of the approach also in demanding scenarios with real-time constraints on the computation. This paper was motivated by the problem of generating movements to transfer a robot from its current state to a new position and velocity at a certain time, when the target state and the final time may require correction at a high rate. For example, for picking small objects from a conveyor belt with a variable feed rate, an off-line planning would fail, since the motion has to be adjusted as soon as the speed is changed. Under the assumption that the desired pickup position and velocity and arrival time can be predicted, the approach in this paper is applicable. The movements can be optimized, for example, for energy efficiency or for reduction of vibrations in the robot. We discuss how to mathematically express the desired performance criteria and other requirements on the motion, such as not violating a maximum joint speed. Quick reactions to sensor inputs are computationally demanding. Thus, we limit ourselves to a class of motion-generation problems that lends itself to numerical optimization. Additionally, we save computation power by gradually refining the motion.

In the framework of robotics, Reinforcement Learning (RL) deals with the learning of a task by the robot itself. This paper presents a hierarchical-planning approach in which the robot learns the optimal behavior for different levels in a decoupled way. For high-level discrete actions, Q-learning was chosen, whereas for the low level we utilize Policy Improvement with Path Integrals (PI2) algorithm to learn the parameters of policies, represented by rhythmic Dynamic Movement Primitives (DMPs). The paper studies the case of a 4-finger-gripper manipulator, which performs the task of continuously spinning a ball around a desired axis. The results demonstrate the efficacy of the hierarchical planning and the increased performance of the task when PI2is used in conjunction with rhythmic DMPs in a real environment.

Programming robots for tasks involving force interaction is difficult, since both the knowledge of the task and the dynamics of the robots are necessary. An immersive haptic interface for task demonstration is proposed, where the operator can sense and act through the robot. This is achieved by coupling two robotic systems with virtual constraints such that they have the same coordinates in the operational space disregarding a fixed offset. Limitations caused by the singular configurations or the reach of the robots are naturally reflected to either side as haptic feedback.

In modern day industry, robots are indispensable for achieving high production rates and competitiveness. In small and medium scale enterprises, where the production may shift rapidly, it is vital to be able to reprogram robots quickly. Kinesthetic teaching, also known as lead-through programming (LTP), provides a fast approach for teaching a trajectory. In this approach, a trajectory is demonstrated by physical interaction with the robot, i.e., the user manually guides the manipulator. This paper presents a sensorless approach to LTP for redundant robots that eliminates the need for expensive force/torque sensors. The active implementation enhances the passive LTP by an admittance control in joint space based on the external forces applied by the user, estimated with a Kalman filter using the generalized momentum formulation. To improve the quality of the estimation and hence LTP, we use a dithering technique. The active LTP has been implemented on ABB YuMi robot and experimental comparison with an earlier passive LTP is presented.

Industrial robots are important when the degree of automation in industry is increased. To enable the use of robots also when the products change rapidly, the programming must be quick and easy to perform. One way to accomplish this is to use lead-through programming, i.e., the user manually guides the robot. This paper presents a sensorless approach, and thus avoids the need for a typically expensive sensor. The method is based on disabling low-level joint controllers combined with gravity compensation. It is reported how the performance can be improved by compensating for friction. Further, a method for detecting small external torques is described, based on the use of the low-level joint controllers with increased integral gain. The lead-through programming is experimentally evaluated using two different industrial robots.