Integrating physics-based prediction with Semantic plan Execution Monitoring

Rockel, Sebastian; Konečný, Štefan; Stock, Sebastian; Hertzberg, Joachim; Pecora, Federico; Zhang, Jianwei

doi:10.1109/iros.2015.7353774

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Naively, this can be achieved by modeling specific thresholds for the manipulation costs. Common physics-based validation methods like the one of Rockel et al [33] determine such thresholds heuristically which signal whether or not some object is currently regarded as toppling. Pastor et al [34], on the other hand, use statistical methods to determine if a particular motion coincides with a predefined spatial envelope.…”

Section: Damage-avoiding Manipulation Sequence Planningmentioning

confidence: 99%

Self-supervised damage-avoiding manipulation strategy optimization via mental simulation

Doernbach

2019

Intel Serv Robotics

View full text Add to dashboard Cite

Everyday robotics are challenged to deal with autonomous product handling in applications like logistics or retail, possibly causing damage on the items during manipulation. Traditionally, most approaches try to minimize physical interaction with goods. However, this paper proposes to take into account any unintended object motion and to learn damage-minimizing manipulation strategies in a self-supervised way. The presented approach consists of a simulation-based planning method for an optimal manipulation sequence with respect to possible damage. The planned manipulation sequences are generalized to new, unseen scenes in the same application scenario using machine learning. This learned manipulation strategy is continuously refined in a self-supervised, simulationin-the-loop optimization cycle during load-free times of the system, commonly known as mental simulation. In parallel, the generated manipulation strategies can be deployed in near-real time in an anytime fashion. The approach is validated on an industrial container-unloading scenario and on a retail shelf-replenishment scenario.

show abstract

Section: Damage-avoiding Manipulation Sequence Planningmentioning

confidence: 99%

Self-supervised damage-avoiding manipulation strategy optimization via mental simulation

Doernbach

2019

Intel Serv Robotics

View full text Add to dashboard Cite

show abstract

“…In the robotics community, the idea of using simulators to improve execution is not new. Rockel et al [13] show a system where simulation is integrated into the planner, such that the latter can choose the appropriate action and parameters based on simulation. This allows the robot to learn a new skill such as balancing an object on a tray.…”

Section: Related Workmentioning

confidence: 99%

Specializing Underdetermined Action Descriptions Through Plan Projection

Kazhoyan¹,

Beetz²

2018

Preprint

View full text Add to dashboard Cite

Plan execution on real robots in realistic environments is underdetermined and often leads to failures. The choice of action parameterization is crucial for task success. By thinking ahead of time with the fast plan projection mechanism proposed in this paper, a general plan can be specialized towards the environment and task at hand by choosing action parameterizations that are predicted to lead to successful execution. For finding causal relationships between action parameterizations and task success, we provide the robot with means for plan introspection and propose a systematic and hierarchical plan structure to support that. We evaluate our approach by showing how a PR2 robot, when equipped with the proposed system, is able to choose action parameterizations that increase task execution success rates and overall performance of fetch and deliver actions in a real world setting.

show abstract

“…One drawback of using Scene Dynamics Anticipation as a validation method, however, is the fact that it outputs the manipulation costs for the given scene configuration, but classification between positively and negatively validated actions has to be performed manually via a threshold. This is a common problem for Outcome Prediction methods in general, also for Rockel et al's approach [10] where thresholds are defined manually for which an object is considered to be toppling. Another example is [8] where the authors perform statistical tests on whether a planned motion lies within a learned envelope.…”

Section: Manipulation Outcome Predictionmentioning

confidence: 99%

“…In contrast to these works, Rockel et al [10] present an interesting idea of predicting task success on the basis of motion of the manipulated objects. Concretely, their application includes a robot which maximizes its speed moving around in a scene, but without losing the balance of an object which sits on its base.…”

Section: B Manipulation Strategy Planningmentioning

confidence: 99%

Physics-based damage-aware manipulation strategy planning using Scene Dynamics Anticipation

Fromm

Birk

2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-We present a damage-aware planning approach which determines the best sequence to manipulate a number of objects in a scene. This works on task-planning level, abstracts from motion planning and anticipates the dynamics of the scene using a physics simulation. Instead of avoiding interaction with the environment, we take unintended motion of other objects into account and plan manipulation sequences which minimize the potential damage. Our method can also be used as a validation measure to judge planned motions for their feasibility in terms of damage avoidance. We evaluate our approach on one industrial scenario (autonomous container unloading) and one retail scenario (shelf replenishment).

show abstract

Integrating physics-based prediction with Semantic plan Execution Monitoring

Cited by 7 publications

References 13 publications

Self-supervised damage-avoiding manipulation strategy optimization via mental simulation

Self-supervised damage-avoiding manipulation strategy optimization via mental simulation

Specializing Underdetermined Action Descriptions Through Plan Projection

Physics-based damage-aware manipulation strategy planning using Scene Dynamics Anticipation

Contact Info

Product

Resources

About