skip to main content


Title: Safe and Coordinated Hierarchical Receding Horizon Control for Mobile Manipulators
Mobile manipulators, constructed by mobile platforms and manipulators, have become a promising solution to future factories for introducing flexibility to manufacturing. This paper presents a method, hierarchical receding horizon control algorithm (HRHC), to assure safety and achieve higher time and space efficiency in robots surrounded by time-varying environments. HRHC contains an optimization based motion planning module that takes account of both the mobile platform and the manipulator to utilize the kinematic redundancy, and a low-level safety controller to deal with fast changes in the environment. With this method, we verify the performance through experiments. The result shows that space efficiency is increased and the HRHC can guarantee local safety in dynamic environments.  more » « less
Award ID(s):
1734109
NSF-PAR ID:
10213594
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Safe and Coordinated Hierarchical Receding Horizon Control for Mobile Manipulators
Page Range / eLocation ID:
2143 to 2149
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Cooperatively avoiding collision is a critical functionality for robots navigating in dense human crowds, failure of which could lead to either overaggressive or overcautious behavior. A necessary condition for cooperative collision avoidance is to couple the prediction of the agents’ trajectories with the planning of the robot’s trajectory. However, it is unclear that trajectory based cooperative collision avoidance captures the correct agent attributes. In this work we migrate from trajectory based coupling to a formalism that couples agent preference distributions. In particular, we show that preference distributions (probability density functions representing agents’ intentions) can capture higher order statistics of agent behaviors, such as willingness to cooperate. Thus, coupling in distribution space exploits more information about inter-agent cooperation than coupling in trajectory space. We thus introduce a general objective for coupled prediction and planning in distribution space, and propose an iterative best response optimization method based on variational analysis with guaranteed sufficient decrease. Based on this analysis, we develop a sampling-based motion planning framework called DistNav1 that runs in real time on a laptop CPU. We evaluate our approach on challenging scenarios from both real world datasets and simulation environments, and benchmark against a wide variety of model based and machine learning based approaches. The safety and efficiency statistics of our approach outperform all other models. Finally, we find that DistNav is competitive with human safety and efficiency performance. 
    more » « less
  2. Background: The increasing prevalence of robots in industrial environments is attributed in part to advancements in collaborative robot technologies, enabling robots to work in close proximity to humans. Simultaneously, the rise of teleoperation, involving remote robot control, poses unique opportunities and challenges for human-robot collaboration (HRC) in diverse and distributed workspaces. Purpose: There is not yet a comprehensive understanding of HRC in teleoperation, specifically focusing on collaborations involving the teleoperator, the robot, and the local or onsite workers in industrial settings, here referred to as teleoperator-robot-human collaboration (tRHC). We aimed to identify opportunities, challenges, and potential applications of tRHC through insights provided from industry stakeholders, thereby supporting effective future industrial implementations. Methods: Thirteen stakeholders in robotics, specializing in different domains (i.e., safety, robot manufacturing, aerospace/automotive manufacturing, and supply chains), completed semi-structured interviews that focused on exploring diverse aspects relevant to tRHC. The interviews were then transcribed and thematic analysis was applied to group responses into broader categories, which were further compared across stakeholder industries. Results We identified three main categories and 13 themes from the interviews. These categories include Benefits, Concerns, and Technical Challenges. Interviewees highlighted accessibility, ergonomics, flexibility, safety, time & cost saving, and trust as benefits of tRHC. Concerns raised encompassed safety, standards, trust, and workplace optimization. Technical challenges consisted of critical issues such as communication time delays, the need for high dexterity in robot manipulators, the importance of establishing shared situational awareness among all agents, and the potential of augmented and virtual reality in providing immersive control interfaces. Conclusions: Despite important challenges, tRHC could offer unique benefits, facilitating seamless collaboration among the teleoperator, teleoperated robot(s), and onsite workers across physical and geographic boundaries. To realize such benefits and address the challenges, we propose several research directions to further explore and develop tRHC capabilities. 
    more » « less
  3. Autonomous mobile robots deployed in outdoor environments must reason about different types of terrain for both safety (e.g., prefer dirt over mud) and deployer preferences (e.g., prefer dirt path over flower beds). Most existing solutions to this preference-aware path planning problem use semantic segmentation to classify terrain types from camera images, and then ascribe costs to each type. Unfortunately, there are three key limitations of such approaches -- they 1) require pre-enumeration of the discrete terrain types, 2) are unable to handle hybrid terrain types (e.g., grassy dirt), and 3) require expensive labelled data to train visual semantic segmentation. We introduce Visual Representation Learning for Preference-Aware Path Planning (VRL-PAP), an alternative approach that overcomes all three limitations: VRL-PAP leverages unlabeled human demonstrations of navigation to autonomously generate triplets for learning visual representations of terrain that are viewpoint invariant and encode terrain types in a continuous representation space. The learned representations are then used along with the same unlabeled human navigation demonstrations to learn a mapping from the representation space to terrain costs. At run time, VRL-PAP maps from images to representations and then representations to costs to perform preference-aware path planning. We present empirical results from challenging outdoor settings that demonstrate VRL-PAP 1) is successfully able to pick paths that reflect demonstrated preferences, 2) is comparable in execution to geometric navigation with a highly detailed manually annotated map (without requiring such annotations), 3) is able to generalize to novel terrain types with minimal additional unlabeled demonstrations. 
    more » « less
  4. Abstract

    Autonomous aerial manipulators have great potentials to assist humans or even fully automate manual labor-intensive tasks such as aerial cleaning, aerial transportation, infrastructure repair, and agricultural inspection and sampling. Reinforcement learning holds the promise of enabling persistent autonomy of aerial manipulators because it can adapt to different situations by automatically learning optimal policies from the interactions between the aerial manipulator and environments. However, the learning process itself could experience failures that can practically endanger the safety of aerial manipulators and hence hinder persistent autonomy. In order to solve this problem, we propose for the aerial manipulator a self-reflective learning strategy that can smartly and safely finding optimal policies for different new situations. This self-reflective manner consists of three steps: identifying the appearance of new situations, re-seeking the optimal policy with reinforcement learning, and evaluating the termination of self-reflection. Numerical simulations demonstrate, compared with conventional learning-based autonomy, our strategy can significantly reduce failures while still can finish the given task.

     
    more » « less
  5. null (Ed.)
    Abstract

    Mobile Cable-Driven Parallel Manipulators (m-CDPM) are a sub-class of CDPM with greater-capabilities (antagonistic cable-tensioning and reconfigurability) by virtue of mobility of the base-winches. In past work, we had also explored creation of adjustable spring-stiffness modules, in-line with cables, which decouple cable-stiffness and cable-tensions. All these internal-freedoms allow an m-CDPM to track desired trajectories while equilibrating end-effector wrenches and improving lateral disturbance-rejection. However, parameter and configuration selection is key to unlocking these benefits.

    To this end, we consider an approach to partition task-execution into a primary (fast) winch-tension control and secondary (slow) reconfiguration and joint-stiffness modulation. This would enable a primary trajectory-tracking task together with secondary task-space stiffness tailoring, using system-reconfiguration and joint-stiffness modulation. In this paper, we limit our scope to feasibility-evaluation to achieve the stiffness modulation as a secondary goal within an offline design-optimization setting (but with an eye towards real-time implementation).

    These aspects are illustrated in the context of a 3-PRP m-CDPM for tracking a desired trajectory within its wrench-feasible workspace. The secondary-task is the directional-alignment and shaping of the stiffness ellipsoid to shape the disturbance-rejection characteristics along the trajectory. The optimization is solved through constrained minimization of a multi-objective weighted cost function subject to non-linear workspace feasibility, and inequality stiffness and tension constraints.

     
    more » « less