Fetch Robot Research Articles

Should I Just Stick to the Wall? Evaluating the Social Acceptance and Preferred Driving Side of Wall Following

The need for safe, predictable, and reliable robot navigation is fundamental for mobile robots to move around in home and office environments. Shortest-path navigation is a popular robot navigation method that uses the most efficient path to get to the desired goal. This behaviour is not always easy to interpret, understand, and avoid in a congested hallway. Instead, more predictable navigation methods, such as a robot following a wall, can help increase social acceptance and help avoid the robot crossing the pedestrian path. If a robot follows along a wall, a key variable to consider is the preferred driving side of the robot (left or right) in areas such as in narrow passages, and its perceived impact on social acceptance. This international user study (n = 143) involved an online video-based test to compare robot evaluation and social acceptance for two types of mobile navigation (Wall-Following and Shortest Path), including the preferred driving side for Wall-Following. A Fetch robot navigated from start to goal position in a series of indoor scenarios with a pedestrian. Select scenarios included a hallway, doorway, and intersection. Independent Sample T-Tests results found that Wall-Following was rated significantly higher than Shortest Path for being perceived as more comfortable and predictable, regardless of robot driving side. The preference for the driver side of the robot did not match the country of residence, nor did it have a significant impact on robot ratings. There were significant interaction effects for comfort, safety and predictable scores across two timepoints. Given the popularity of Shortest Path navigation, the findings indicate that this approach might not be the most appropriate for human settings. Additional investigation into Wall-Following behaviours is recommended for social acceptance, even if the method compromises the efficiency of the robot to acheive its objective.

Interaction-Driven Active 3D Reconstruction with Object Interiors

We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction , and 3D scanning to recover both the exterior and interior , i.e., unexposed, geometries of a target 3D object. Unlike other works in active vision which focus on optimizing camera viewpoints to better investigate the environment, the primary feature of our reconstruction is an analysis of the interactability of various parts of the target object and the ensuing part manipulation by a robot to enable scanning of occluded regions. As a result, an understanding of part articulations of the target object is obtained on top of complete geometry acquisition. Our method operates fully automatically by a Fetch robot with built-in RGBD sensors. It iterates between interaction analysis and interaction-driven reconstruction, scanning and reconstructing detected moveable parts one at a time, where both the articulated part detection and mesh reconstruction are carried out by neural networks. In the final step, all the remaining, non-articulated parts, including all the interior structures that had been exposed by prior part manipulations and subsequently scanned, are reconstructed to complete the acquisition. We demonstrate the performance of our method via qualitative and quantitative evaluation, ablation studies, comparisons to alternatives, as well as experiments in a real environment.

Solving Rearrangement Puzzles Using Path Defragmentation in Factored State Spaces

Rearrangement puzzles are variations of rearrangement problems in which the elements of a problem are potentially logically linked together. To efficiently solve such puzzles, we develop a motion planning approach based on a new state space that is logically <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">factored</i> , integrating the capabilities of the robot through factors of simultaneously manipulatable joints of an object. Based on this factored state space, we propose less-actions RRT (LA-RRT), a planner which optimizes for a low number of actions to solve a puzzle. At the core of our approach lies a new path defragmentation method, which rearranges and optimizes consecutive edges to minimize action cost. We solve six rearrangement scenarios with a Fetch robot, involving planar table puzzles and an escape room scenario. LA-RRT significantly outperforms the next best asymptotically-optimal planner by 4.01 to 6.58 times improvement in final action cost.

Super Intendo: Semantic Robot Programming from Multiple Demonstrations for taskable robots

When an end-user instructs a taskable robot on a new task, it is important for the robot to learn the user’s intention for the task. Knowing the user’s intention, represented as desired goal conditions, allows the robot to generalize across variations of the learned task seen at execution time. However, it has proven challenging to learn goal conditions due to the large, noisy, and complex space of goal conditions expressed by human users. This paper introduces Semantic Robot Programming with Multiple Demonstrations (SRP-MD) to learn a generative model of latent end-user task goal conditions from multiple end-user demonstrations in a shared workspace. By learning a generative model of the goal conditions, SRP-MD generalizes to task instances even when the quantity of objects to be arranged is not in the training set or novel object instances are included. At test time, a new goal is pulled from the learned generative model given the objects present in the initial scene. The efficacy of SRP-MD as a step toward taskable robots is shown on a Fetch robot learning and executing bin packing tasks in a simulated environment with grocery items.

Navigating Robots in Dynamic Environment With Deep Reinforcement Learning

In the fight against COVID-19, many robots replace human employees in various tasks that involve a risk of infection. Among these tasks, the fundamental problem of navigating robots among crowds, named robot crowd navigation, remains open and challenging. Therefore, we propose HGAT-DRL, a heterogeneous GAT-based deep reinforcement learning algorithm. This algorithm encodes the constrained human-robot-coexisting environment in a heterogeneous graph consisting of four types of nodes. It also constructs an interactive agent-level representation for objects surrounding the robot, and incorporates the kinodynamic constraints from the non-holonomic motion model into the deep reinforcement learning (DRL) framework. Simulation results show that our proposed algorithm achieves a success rate of 92%, at least 6% higher than four baseline algorithms. Furthermore, the hardware experiment on a Fetch robot demonstrates our algorithm’s successful and convenient migration to real robots.

Submap-Based Indoor Navigation System for the Fetch Robot

In this paper, we present a novel navigation framework for the Fetch robot in a large-scale environment based on submapping techniques. This indoor navigation system is divided into a submap mapping part and an on-line localization part. For the mapping part, in order to deal with large environments or multi-story buildings, a submap mapping framework fusing two-dimensional (2D) laser scan and 3D point cloud from RGBD sensor is proposed using Google Cartographer. Meanwhile, several image datasets with corresponding poses are created from the RGBD sensor. Thanks to the submap framework, the error is limited corresponding to the size of the map, thus localization accuracy will be improved. For the on-line localization, so as to switch the submaps, the on-line images from the RGBD sensor are used to match the database images using DeepLCD, a deep learning based library for loop closure. Based on the information from DeepLCD and odometry, adaptive Monte Carlo localization (AMCL) is reinitialized to finish the localization task. In order to validate the result accuracy, reflectors and a motion capture system are used to compute the absolute trajectory error (ATE) and the relative pose error (RPE) based on the Gaussian-Newton (GN) algorithm. Finally, the proposed framework is tested on the Fetch simulator and the real Fetch robot, including both submap mapping and on-line localization.

Multi-task trust transfer for human–robot interaction

Trust is essential in shaping human interactions with one another and with robots. In this article we investigate how human trust in robot capabilities transfers across multiple tasks. We present a human-subject study of two distinct task domains: a Fetch robot performing household tasks and a virtual reality simulation of an autonomous vehicle performing driving and parking maneuvers. The findings expand our understanding of trust and provide new predictive models of trust evolution and transfer via latent task representations: a rational Bayes model, a data-driven neural network model, and a hybrid model that combines the two. Experiments show that the proposed models outperform prevailing models when predicting trust over unseen tasks and users. These results suggest that (i) task-dependent functional trust models capture human trust in robot capabilities more accurately and (ii) trust transfer across tasks can be inferred to a good degree. The latter enables trust-mediated robot decision-making for fluent human–robot interaction in multi-task settings.

The Exchange of Knowledge Using Cloud Robotics

To enable robots to perform human-level tasks flexibly in varying conditions, we need a mechanism that allows them to exchange knowledge between themselves for crowd-sourcing the knowledge gap problem. One approach to achieve this is to equip a cloud application with a range of encyclopedic knowledge (i.e. ontologies) and execution logs of different robots performing the same tasks in different environments. In this paper, we show how knowledge exchange between robots can be done using OPENEASE as the cloud application. We equipped OPENEASE with ontologies about the kitchen domain, execution logs of three robots operating in two different kitchens, and semantic descriptions of both environments. By addressing two different use cases, we show that two PR2 robots and one Fetch robot can successfully adapt each other's plan parameters and sub symbolic data to the experiments that they are conducting.