Robot Learning of Mobile Manipulation With Reachability Behavior Priors

Jauhri, Snehal; Peters, Jan; Chalvatzaki, Georgia

doi:10.1109/lra.2022.3188109

Cited by 20 publications

(16 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pick-and-place task showed the capacity of the proposed learning and optimization framework, which can be directly applied to other loco-manipulation scenarios, for example, the door-opening task in [13]. Although we evaluated the demonstrated pick-and-place skills on MOCA, unlike the IRM-based methods for a specific mobile manipulator, it is possible to apply the learned skills to other MMs, such as TIAGo++ in [6], PR2 in [13], NAO humanoid in [9], and even legged MMs [7], as long as the learned EE trajectory is achievable for the MM. Furthermore, owing to the hierarchical design in the proposed HQP, the learned EE trajectory was tracked accurately, and the base pose was followed as a secondary priority, which allowed the transfer of the human whole-body mobile manipulation skills to a robot with different geometry.…”

Section: Results and Discussion 1) Human Demonstrations Analysismentioning

confidence: 99%

“…Specifically, for a given endeffector's (EE) pose of the MM, the proper poses of the mobile base and feasible configurations of the robotic arm can be found by querying IRM. Recently, the IRM has been applied as priors in the reinforcement learning (RL) method in [6] to accelerate the learning process. Although IRM can be generated offline and searched online, its construction is non-trivial.…”

Section: Pick Replacementioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks With Mobile Manipulators

Jianzhuang

Giammarino

Lamon

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

This letter proposes a hybrid learning and optimization framework for mobile manipulators for complex and physically interactive tasks. The framework exploits an admittance-type physical interface to obtain intuitive and simplified human demonstrations and Gaussian Mixture Model (GMM)/Gaussian Mixture Regression (GMR) to encode and generate the learned task requirements in terms of position, velocity, and force profiles. Next, using the desired trajectories and force profiles generated by GMM/GMR, the impedance parameters of a Cartesian impedance controller are optimized online through a Quadratic Program augmented with an energy tank to ensure the passivity of the controlled system. Two experiments are conducted to validate the framework, comparing our method with two approaches with constant stiffness (high and low). The results showed that the proposed method outperforms the other two cases in terms of trajectory tracking and generated interaction forces, even in the presence of disturbances such as unexpected end-effector collisions.

show abstract

Section: Results and Discussion 1) Human Demonstrations Analysismentioning

confidence: 99%

Section: Pick Replacementioning

confidence: 99%

A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks With Mobile Manipulators

Jianzhuang

Giammarino

Lamon

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…In general, the goal is to find a pose for which the target is reachable with a collisionfree configuration of the robot [5]. Approaches typically aim to generate solutions that are optimal against some other metric such as manipulability [6], [7], or stiffness of the robot [8]. Other approaches aim to minimise task time by calculating base poses from which multiple targets can be reached without repositioning [9], [10].…”

Section: Related Workmentioning

confidence: 99%

An Architecture for Reactive Mobile Manipulation On-The-Move

Ben

Lehnert

Leitner³

et al. 2023

2023 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We present a reactive base control method that enables high performance mobile manipulation on-the-move in environments with static and dynamic obstacles. Performing manipulation tasks while the mobile base remains in motion can significantly decrease the time required to perform multistep tasks, as well as improve the gracefulness of the robot's motion. Existing approaches to manipulation on-the-move either ignore the obstacle avoidance problem or rely on the execution of planned trajectories, which is not suitable in environments with dynamic objects and obstacles. The presented controller addresses both of these deficiencies and demonstrates robust performance of pick-and-place tasks in dynamic environments. The performance is evaluated on several simulated and real-world tasks. On a real-world task with static obstacles, we outperform an existing method by 48% in terms of total task time. Further, we present real-world examples of our robot performing manipulation tasks onthe-move while avoiding a second autonomous robot in the workspace. See benburgesslimerick.github.io/MotM-BaseControl for supplementary materials.

show abstract

“…the inversion of the object’s reachability map (IRM) (Vahrenkamp et al , 2013). As IRM consists of infinite positions that enable the manipulator to reach the target object (Jauhri et al , 2022), a criterion for the comparison of the manipulator’s operation performance is required to assist final decision-making.…”

Section: Related Workmentioning

confidence: 99%

Pose optimization for mobile manipulator grasping based on hybrid manipulability

Xie,

Liu,

Yang

2023

View full text Add to dashboard Cite

Purpose Proper platform pose is important for the mobile manipulator to accomplish dexterous manipulation tasks efficiently and safely, and the evaluation criterion to qualify manipulation performance is critical to support the pose decision process. This paper aims to present a comprehensive index to evaluate the manipulator’s operation performance from various aspects. Design/methodology/approach In this research, a criterion called hybrid manipulability (HM) is proposed to assess the performance of the manipulator’s operation, considering crucial factors such as joint limits, obstacle avoidance and stability. The determination of the optimal platform pose is achieved by selecting the pose that maximizes the HM within the feasible inverse reachability map associated with the target object. Findings A self-built mobile manipulator is adopted as the experimental platform, and the feasibility of the proposed method is experimentally verified in the context of object-grasping tasks both in simulation and practice. Originality/value The proposed HM extends upon the conventional notion of manipulability by incorporating additional factors, including the manipulator’s joint limits, the obstacle avoidance situation during the operation and the manipulation stability when grasping the target object. The manipulator can achieve enhanced stability during grasping when positioned in the pose determined by the HM.

show abstract

Robot Learning of Mobile Manipulation With Reachability Behavior Priors

Cited by 20 publications

References 44 publications

A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks With Mobile Manipulators

A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks With Mobile Manipulators

An Architecture for Reactive Mobile Manipulation On-The-Move

Pose optimization for mobile manipulator grasping based on hybrid manipulability

Contact Info

Product

Resources

About