Real-time optimized inverse kinematics of redundant robots under inequality constraints

Inverse kinematics of redundant robots presents a challenging problem for real-time applications due to the lack of uniqueness of solution and the low computational efficiency caused by redundancy and hard limits. In this work, a general and efficient method for addressing the real-time optimized inverse kinematics of redundant robots is proposed, taking into account hard limits in joint and Cartesian space that can never be violated. The proposed method proceeds by using constrained linear programming instead of quadratic programming to solve the inverse kinematics problem. Various hard limits such as joint range, bounds on velocity and acceleration are handled explicitly as inequality constraints. This method resolves the redundancy in real-time and enable to simultaneously guarantee that the additional motion constraints will never be violated. Its performance allows real-time kinematic control of redundant robots executing sensor-driven online tasks. The effectiveness of this method is demonstrated through simulations and experiments conducted on a 7-DOF KUKA IIWA robot, showcasing its ability to control redundant robots executing sensor-driven tasks in dynamic environments with numerous hard limits.

Peg-in-hole assembly skill imitation learning method based on ProMPs under task geometric representation

Introduction

Behavioral Cloning (BC) is a common imitation learning method which utilizes neural networks to approximate the demonstration action samples for task manipulation skill learning. However, in the real world, the demonstration trajectories from human are often sparse and imperfect, which makes it challenging to comprehensively learn directly from the demonstration action samples. Therefore, in this paper, we proposes a streamlined imitation learning method under the terse geometric representation to take good advantage of the demonstration data, and then realize the manipulation skill learning of assembly tasks.

Methods

We map the demonstration trajectories into the geometric feature space. Then we align the demonstration trajectories by Dynamic Time Warping (DTW) method to get the unified data sequence so we can segment them into several time stages. The Probability Movement Primitives (ProMPs) of the demonstration trajectories are then extracted, so we can generate a lot of task trajectories to be the global strategy action samples for training the neural networks. Notalby, we regard the current state of the assembly task as the via point of the ProMPs model to get the generated trajectories, while the time point of the via point is calculated according to the probability model of the different time stages. And we get the action of the current state according to the target position of the next time state. Finally, we train the neural network to obtain the global assembly strategy by Behavioral Cloning.

Results

We applied the proposed method to the peg-in-hole assembly task in the simulation environment based on Pybullet + Gym to test its task skill learning performance. And the learned assembly strategy was also executed on a real robotic platform to verify the feasibility of the method further.

Discussion

According to the result of the experiment, the proposed method achieves higher success rates compared to traditional imitation learning methods while exhibiting reasonable generalization capabilities. It shows that the ProMPs under geometric representation can help the BC method make better use of the demonstration trajectory and thus better learn the task skills.

A Robot Motion Learning Method Using Broad Learning System Verified by Small-Scale Fish-Like Robot

The widespread application of learning-based methods in robotics has allowed significant simplifications to controller design and parameter adjustment. In this article, robot motion is controlled with learning-based methods. A control policy using a broad learning system (BLS) for robot point-reaching motion is developed. A sample application based on a magnetic small-scale robotic system is designed without detailed mathematical modeling of the dynamic systems. The parameter constraints of the nodes in the BLS-based controller are derived based on Lyapunov theory. The design and control training processes for a small-scale magnetic fish motion are presented. Finally, the effectiveness of the proposed method is demonstrated by convergence of the artificial magnetic fish motion to the targeted area with the BLS trajectory, successfully avoiding obstacles.

A Learning-Based Stable Servo Control Strategy Using Broad Learning System Applied for Microrobotic Control

As the controller parameter adjustment process is simplified significantly by using learning algorithms, the studies about learning-based control attract a lot of interest in recent years. This article focuses on the intelligent servo control problem using learning from desired demonstrations. Compared with the previous studies about the learning-based servo control, a control policy using the broad learning system (BLS) is developed and first applied to a microrobotic system, since the advantages of the BLS, such as simple structure and no-requirement for retraining when new demos' data is provided. Then, the Lyapunov theory is skillfully combined with the complex learning algorithm to derive the controller parameters' constraints. Thus, the final control policy not only can obtain the movement skills of the desired demonstrations but also have the strong ability of generalization and error convergence. Finally, simulation and experimental examples verify the effectiveness of the proposed strategy using MATLAB and a microswimmer trajectory tracking system.

How to compete with robots by assessing job automation risks and resilient alternatives

The effects of robotics and artificial intelligence (AI) on the job market are matters of great social concern. Economists and technology experts are debating at what rate, and to what extent, technology could be used to replace humans in occupations, and what actions could mitigate the unemployment that would result. To this end, it is important to predict which jobs could be automated in the future and what workers could do to move to occupations at lower risk of automation. Here, we calculate the automation risk of almost 1000 existing occupations by quantitatively assessing to what extent robotics and AI abilities can replace human abilities required for those jobs. Furthermore, we introduce a method to find, for any occupation, alternatives that maximize the reduction in automation risk while minimizing the retraining effort. We apply the method to the U.S. workforce composition and show that it could substantially reduce the workers' automation risk, while the associated retraining effort would be moderate. Governments could use the proposed method to evaluate the unemployment risk of their populations and to adjust educational policies. Robotics companies could use it as a tool to better understand market needs, and members of the public could use it to identify the easiest route to reposition themselves on the job market.

Learning from demonstration using products of experts: Applications to manipulation and task prioritization

Probability distributions are key components of many learning from demonstration (LfD) approaches, with the spaces chosen to represent tasks playing a central role. Although the robot configuration is defined by its joint angles, end-effector poses are often best explained within several task spaces. In many approaches, distributions within relevant task spaces are learned independently and only combined at the control level. This simplification implies several problems that are addressed in this work. We show that the fusion of models in different task spaces can be expressed as products of experts (PoE), where the probabilities of the models are multiplied and renormalized so that it becomes a proper distribution of joint angles. Multiple experiments are presented to show that learning the different models jointly in the PoE framework significantly improves the quality of the final model. The proposed approach particularly stands out when the robot has to learn hierarchical objectives that arise when a task requires the prioritization of several sub-tasks (e.g. in a humanoid robot, keeping balance has a higher priority than reaching for an object). Since training the model jointly usually relies on contrastive divergence, which requires costly approximations that can affect performance, we propose an alternative strategy using variational inference and mixture model approximations. In particular, we show that the proposed approach can be extended to PoE with a nullspace structure (PoENS), where the model is able to recover secondary tasks that are masked by the resolution of tasks of higher-importance.