Towards Mobile Multi-Task Manipulation in a Confined and Integrated Environment with Irregular Objects

Han, Zhao; Allspaw, Jordan; LeMasurier, Gregory; Parrillo, Jenna; Giger, Daniel; Ahmadzadeh, S. Reza; Yanco, Holly A.

doi:10.1109/icra40945.2020.9197395

Cited by 19 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These issues (i.e., multimodal perception, manipulation planning and reasoning, system-level integration, speed of execution, and whole-body coordination) continue to be the main challenges in mobile manipulation systems, as observed during other recent competitions [10], [11], [13]. A more recent development is the introduction of competitions that focus on learning-based approaches, e.g., the Real Robot Challenge by the MPI-IS in 2020.…”

Section: Further Technical Advances Requiredmentioning

confidence: 99%

See 1 more Smart Citation

Mobile Manipulation Hackathon: Moving into Real World Applications

Roa

Dogar

Pagès³

et al. 2021

IEEE Robot. Automat. Mag.

View full text Add to dashboard Cite

Section: Further Technical Advances Requiredmentioning

confidence: 99%

“…The FetchIt! Mobile Manipulation Challenge was held at the 2019 IEEE International Conference on Robotics and Automation [10]. The task was to assemble a kit formed by six objects obtained from stations around a designated arena, combining navigation and manipulation skills.…”

Section: Related Hackathons and Competitionsmentioning

confidence: 99%

Mobile Manipulation Hackathon: Moving into Real World Applications

Roa

Dogar

Pagès³

et al. 2021

IEEE Robot. Automat. Mag.

View full text Add to dashboard Cite

“…The robot needs to first collect two screws from a bin as well as one each of a large gear, small gear, gearbox bottom, and gearbox top piece. We described our efforts to address the challenges present in this task in Reference [21]. While the robot can complete the kitting task alone, the ultimate goal is to apply it to a collaborative scenario where one or two workers stay at the inspection table to inspect and perform the fine motor skills to assemble a functional gearbox (Figure 2) from the parts that the robot collected, requiring human-robot collaboration.…”

Section: The Gearbox Kitting Taskmentioning

confidence: 99%

“…Then, we can find its parent to explain what is being attempted (lines [15][16][17]. Similar to the Fallback node, the failed node is then found to explain what went wrong (lines [18][19][20][21][22]. Lines 25-33 consider the case where a Fallback node has an ancestor Retry node.…”

Section: Supporting Failure Explanation Generationmentioning

confidence: 99%

Building the Foundation of Robot Explanation Generation Using Behavior Trees

Han

Giger

Allspaw

et al. 2021

J. Hum.-Robot Interact.

Self Cite

View full text Add to dashboard Cite

As autonomous robots continue to be deployed near people, robots need to be able to explain their actions. In this article, we focus on organizing and representing complex tasks in a way that makes them readily explainable. Many actions consist of sub-actions, each of which may have several sub-actions of their own, and the robot must be able to represent these complex actions before it can explain them. To generate explanations for robot behavior, we propose using Behavior Trees (BTs), which are a powerful and rich tool for robot task specification and execution. However, for BTs to be used for robot explanations, their free-form, static structure must be adapted. In this work, we add structure to previously free-form BTs by framing them as a set of semantic sets {goal, subgoals, steps, actions} and subsequently build explanation generation algorithms that answer questions seeking causal information about robot behavior. We make BTs less static with an algorithm that inserts a subgoal that satisfies all dependencies. We evaluate our BTs for robot explanation generation in two domains: a kitting task to assemble a gearbox, and a taxi simulation. Code for the behavior trees (in XML) and all the algorithms is available at github.com/uml-robotics/robot-explanation-BTs.

show abstract

“…In recent years, a large number of competitions related to mobile operations have been held, such as the Amazon Robotics Challenge [ 23 , 24 ], the DARPA Robotics Challenge [ 25 ], and the FetchIt! Mobile Manipulation Challenge [ 26 ]. The results of these challenges and projects suggest that the research and application of mobile manipulation is a logical integration of operation, navigation, perception, self-learning and multi-robot collaboration; therefore, we would expect that a mobile manipulators should be able to perform complex tasks in both structured and unstructured environments.…”

Section: Related Workmentioning

confidence: 99%

Mobile Manipulation Integrating Enhanced AMCL High-Precision Location and Dynamic Tracking Grasp

Zhou

Chou

Tuo

et al. 2020

Sensors

View full text Add to dashboard Cite

Mobile manipulation, which has more flexibility than fixed-base manipulation, has always been an important topic in the field of robotics. However, for sophisticated operation in complex environments, efficient localization and dynamic tracking grasp still face enormous challenges. To address these challenges, this paper proposes a mobile manipulation method integrating laser-reflector-enhanced adaptive Monte Carlo localization (AMCL) algorithm and a dynamic tracking and grasping algorithm. First, by fusing the information of laser-reflector landmarks to adjust the weight of particles in AMCL, the localization accuracy of mobile platforms can be improved. Second, deep-learning-based multiple-object detection and visual servo are exploited to efficiently track and grasp dynamic objects. Then, a mobile manipulation system integrating the above two algorithms into a robotic with a 6-degrees-of-freedom (DOF) operation arm is implemented in an indoor environment. Technical components, including localization, multiple-object detection, dynamic tracking grasp, and the integrated system, are all verified in real-world scenarios. Experimental results demonstrate the efficacy and superiority of our method.

show abstract

Towards Mobile Multi-Task Manipulation in a Confined and Integrated Environment with Irregular Objects

Cited by 19 publications

References 23 publications

Mobile Manipulation Hackathon: Moving into Real World Applications

Mobile Manipulation Hackathon: Moving into Real World Applications

Building the Foundation of Robot Explanation Generation Using Behavior Trees

Mobile Manipulation Integrating Enhanced AMCL High-Precision Location and Dynamic Tracking Grasp

Contact Info

Product

Resources

About