Search for: All records

We consider the problem of distributed pose graph optimization (PGO) that has important applications in multi- robot simultaneous localization and mapping (SLAM). We pro- pose the majorization minimization (MM) method for distributed PGO (MM−PGO) that applies to a broad class of robust loss kernels. The MM−PGO method is guaranteed to converge to first-order critical points under mild conditions. Furthermore, noting that the MM−PGO method is reminiscent of proximal methods, we leverage Nesterov’s method and adopt adaptive restarts to accelerate convergence. The resulting accelerated MM methods for distributed PGO—both with a master node in the network (AMM−PGO∗) and without (AMM−PGO#)— have faster convergence in contrast to the MM−PGO method without sacrificing theoretical guarantees. In particular, the AMM−PGO# method, which needs no master node and is fully decentralized, features a novel adaptive restart scheme and has a rate of convergence comparable to that of the AMM−PGO∗ method using a master node to aggregate information from all the nodes. The efficacy of this work is validated through extensive applications to 2D and 3D SLAM benchmark datasets and comprehensive comparisons against existing state-of-the-art methods, indicating that our MM methods converge faster and result in better solutions to distributed PGO. The code is available at https://github.com/MurpheyLab/DPGO. 

Despite theoretical benefits of collaborative robots, disappointing outcomes are well documented by clinical studies, spanning rehabilitation, prostheses, and surgery. Cognitive load theory provides a possible explanation for why humans in the real world are not realizing the benefits of collaborative robots: high cognitive loads may be impeding human performance. Measuring cognitive availability using an electrocardiogram, we ask 25 participants to complete a virtual-reality task alongside an invisible agent that determines optimal performance by iteratively updating the Bellman equation. Three robots assist by providing environmental information relevant to task performance. By enabling the robots to act more autonomously—managing more of their own behavior with fewer instructions from the human—here we show that robots can augment participants’ cognitive availability and decision-making. The way in which robots describe and achieve their objective can improve the human’s cognitive ability to reason about the task and contribute to human–robot collaboration outcomes. Augmenting human cognition provides a path to improve the efficacy of collaborative robots. By demonstrating how robots can improve human cognition, this work paves the way for improving the cognitive capabilities of first responders, manufacturing workers, surgeons, and other future users of collaborative autonomy systems.

 

Early research on physical human–robot interaction (pHRI) has necessarily focused on device design—the creation of compliant and sensorized hardware, such as exoskeletons, prostheses, and robot arms, that enables people to safely come in contact with robotic systems and to communicate about their collaborative intent. As hardware capabilities have become sufficient for many applications, and as computing has become more powerful, algorithms that support fluent and expressive use of pHRI systems have begun to play a prominent role in determining the systems’ usefulness. In this review, we describe a selection of representative algorithmic approaches that regulate and interpret pHRI, describing the progression from algorithms based on physical analogies, such as admittance control, to computational methods based on higher-level reasoning, which take advantage of multimodal communication channels. Existing algorithmic approaches largely enable task-specific pHRI, but they do not generalize to versatile human–robot collaboration. Throughout the review and in our discussion of next steps, we therefore argue that emergent embodied dialogue—bidirectional, multimodal communication that can be learned through continuous interaction—is one of the next frontiers of pHRI. 

This paper proposes a novel approach that enables a robot to learn an objective function incrementally from human directional corrections. Existing methods learn from human magnitude corrections; since a human needs to carefully choose the magnitude of each correction, those methods can easily lead to over-corrections and learning inefficiency. The proposed method only requires human directional corrections — corrections that only indicate the direction of an input change without indicating its magnitude. We only assume that each correction, regardless of its magnitude, points in a direction that improves the robot’s current motion relative to an unknown objective function. The allowable corrections satisfying this assumption account for half of the input space, as opposed to the magnitude corrections which have to lie in a shrinking level set. For each directional correction, the proposed method updates the estimate of the objective function based on a cutting plane method, which has a geometric interpretation. We have established theoretical results to show the convergence of the learning process. The proposed method has been tested in numerical examples, a user study on two human-robot games, and a real-world quadrotor experiment. The results confirm the convergence of the proposed method and further show that the method is significantly more effective (higher success rate), efficient/effortless (less human corrections needed), and potentially more accessible (fewer early wasted trials) than the state-of-the-art robot learning frameworks. 

This paper develops the method of Continuous Pontryagin Differentiable Programming (Continuous PDP), which enables a robot to learn an objective function from a few sparsely demonstrated keyframes. The keyframes, labeled with some time stamps, are the desired task-space outputs, which a robot is expected to follow sequentially. The time stamps of the keyframes can be different from the time of the robot’s actual execution. The method jointly finds an objective function and a time-warping function such that the robot’s resulting trajectory sequentially follows the keyframes with minimal discrepancy loss. The Continuous PDP minimizes the discrepancy loss using projected gradient descent, by efficiently solving the gradient of the robot trajectory with respect to the unknown parameters. The method is first evaluated on a simulated robot arm and then applied to a 6-DoF quadrotor to learn an objective function for motion planning in unmodeled environments. The results show the efficiency of the method, its ability to handle time misalignment between keyframes and robot execution, and the generalization of objective learning into unseen motion conditions. 

Robots have components that work together to accomplish a task. Colloids are particles, usually less than 100 µm, that are small enough that they do not settle out of solution. Colloidal robots are particles capable of functions such as sensing, computation, communication, locomotion and energy management that are all controlled by the particle itself. Their design and synthesis is an emerging area of interdisciplinary research drawing from materials science, colloid science, self-assembly, robophysics and control theory. Many colloidal robot systems approach synthetic versions of biological cells in autonomy and may find ultimate utility in bringing these specialized functions to previously inaccessible locations. This Perspective examines the emerging literature and highlights certain design principles and strategies towards the realization of colloidal robots. 

We present a game benchmark for testing human- swarm control algorithms and interfaces in a real-time, high- cadence scenario. Our benchmark consists of a swarm vs. swarm game in a virtual ROS environment in which the goal of the game is to “capture” all agents from the opposing swarm; the game’s high-cadence is a result of the capture rules, which cause agent team sizes to fluctuate rapidly. These rules require players to consider both the number of agents currently at their disposal and the behavior of their opponent’s swarm when they plan actions. We demonstrate our game benchmark with a default human-swarm control system that enables a player to interact with their swarm through a high-level touchscreen interface. The touchscreen interface transforms player gestures into swarm control commands via a low-level decentralized ergodic control framework. We compare our default human- swarm control system to a flocking-based control system, and discuss traits that are crucial for swarm control algorithms and interfaces operating in real-time, high-cadence scenarios like our game benchmark. Our game benchmark code is available on Github; more information can be found at https: //sites.google.com/view/swarm- game- benchmark. 

We develop an approach to improve the learning capabilities of robotic systems by combining learned predictive models with experience-based state-action policy mappings. Predictive models provide an understanding of the task and the dynamics, while experience-based (model-free) policy mappings encode favorable actions that override planned actions. We refer to our approach of systematically combining model-based and model-free learning methods as hybrid learning. Our approach efficiently learns motor skills and improves the performance of predictive models and experience-based policies. Moreover, our approach enables policies (both model-based and model-free) to be updated using any off-policy reinforcement learning method. We derive a deterministic method of hybrid learning by optimally switching between learning modalities. We adapt our method to a stochastic variation that relaxes some of the key assumptions in the original derivation. Our deterministic and stochastic variations are tested on a variety of robot control benchmark tasks in simulation as well as a hardware manipulation task. We extend our approach for use with imitation learning methods, where experience is provided through demonstrations, and we test the expanded capability with a real-world pick-and-place task. The results show that our method is capable of improving the performance and sample efficiency of learning motor skills in a variety of experimental domains.