Contingent Contact-Based Motion Planning

Páll, Előd; Sieverling, Arne; Brock, Oliver

doi:10.1109/iros.2018.8594365

Cited by 25 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Force control planning [62,43,59,201,140,189,193,117,118,68,75,202,64]. Contact for localization [203,63,204,205,206,68,207…”

Section: Learning and Planning Of Manipulation In Contactmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Robot Manipulation in Contact

Suomalainen¹,

Karayiannidis²,

Kyrki³

2021

Preprint

View full text Add to dashboard Cite

“…Force control planning [62,43,59,201,140,189,193,117,118,68,75,202,64]. Contact for localization [203,63,204,205,206,68,207…”

Section: Learning and Planning Of Manipulation In Contactmentioning

confidence: 99%

“…An interesting approach is to use contacts as localization to mitigate uncertainty; the straightforward approach is to consider point-contacts for localization [203]. An approach beyond contact thresholds is the concept of Contact State (CS), which means finding the exact contact point, or points, of a tool.…”

Section: Planning Of Manipulation In Contactmentioning

confidence: 99%

A Survey of Robot Manipulation in Contact

Suomalainen¹,

Karayiannidis²,

Kyrki³

2021

Preprint

View full text Add to dashboard Cite

“…Rather than strictly avoiding environmental contact as is a standard paradigm for traditional path planning (Choset et al, 2005; LaValle, 2006), the planner may decide to allow obstacle contact if it helps the soft growing robot reach its destination. For example, interactions with obstacles can consolidate many possible paths down to a single path, thereby reducing uncertainty (Páll et al, 2018; Sieverling et al, 2017). These interactions can direct the robot to locations not on a straight line path from its starting point, also reducing the need for designed turns that increase robot complexity.…”

Section: Planning Paths That Exploit Obstaclesmentioning

confidence: 99%

“…In particular, we mathematically formalize obstacle interactions with the soft growing robot and use this formalization to plan paths for the robot to navigate to a destination. Similar to the recent works of Páll et al (2018) and Sieverling et al (2017) that explicitly consider the advantages of obstacle contact for motion planning, namely that it reduces uncertainty in the robot’s motion, our planner generates paths that tolerate and even leverage obstacle collisions when helpful for navigating the soft growing robot to its destination (Figure 1).…”

Section: Introductionmentioning

confidence: 99%

Robust navigation of a soft growing robot by exploiting contact with the environment

Greer

Blumenschein

Alterovitz

et al. 2020

The International Journal of Robotics Research

View full text Add to dashboard Cite

Navigation and motion control of a robot to a destination are tasks that have historically been performed with the assumption that contact with the environment is harmful. This makes sense for rigid-bodied robots where obstacle collisions are fundamentally dangerous. However, because many soft robots have bodies that are low-inertia and compliant, obstacle contact is inherently safe. As a result, constraining paths of the robot to not interact with the environment is not necessary and may be limiting. In this paper, we mathematically formalize interactions of a soft growing robot with a planar environment in an empirical kinematic model. Using this interaction model, we develop a method to plan paths for the robot to a destination. Rather than avoiding contact with the environment, the planner exploits obstacle contact when beneficial for navigation. We find that a planner that takes into account and capitalizes on environmental contact produces paths that are more robust to uncertainty than a planner that avoids all obstacle contact.

show abstract

“…Owing to their compliant nature, soft hands are particularly useful in manipulation tasks where physical interactions between the hand, object, and the environment are expected (Della Santina et al, 2017; Eppner et al, 2015). Leveraging the compliant interactions featured by the underactuated hands, certain manipulation tasks can be robustly achieved in an open-loop manner, which can be very challenging using a fully actuated hand, such as using environmental constraints to grasp objects, or interacting with both the object and the environment at the same time (Hang et al, 2019; Páll et al, 2018; Salvietti et al, 2015).…”

Section: Related Workmentioning

confidence: 99%

Hand–object configuration estimation using particle filters for dexterous in-hand manipulation

Hang

Bircher

Morgan

et al. 2019

The International Journal of Robotics Research

View full text Add to dashboard Cite

We consider the problem of in-hand dexterous manipulation with a focus on unknown or uncertain hand–object parameters, such as hand configuration, object pose within hand, and contact positions. In particular, in this work we formulate a generic framework for hand–object configuration estimation using underactuated hands as an example. Owing to the passive reconfigurability and the lack of encoders in the hand’s joints, it is challenging to estimate, plan, and actively control underactuated manipulation. By modeling the grasp constraints, we present a particle filter-based framework to estimate the hand configuration. Specifically, given an arbitrary grasp, we start by sampling a set of hand configuration hypotheses and then randomly manipulate the object within the hand. While observing the object’s movements as evidence using an external camera, which is not necessarily calibrated with the hand frame, our estimator calculates the likelihood of each hypothesis to iteratively estimate the hand configuration. Once converged, the estimator is used to track the hand configuration in real time for future manipulations. Thereafter, we develop an algorithm to precisely plan and control the underactuated manipulation to move the grasped object to desired poses. In contrast to most other dexterous manipulation approaches, our framework does not require any tactile sensing or joint encoders, and can directly operate on any novel objects, without requiring a model of the object a priori. We implemented our framework on both the Yale Model O hand and the Yale T42 hand. The results show that the estimation is accurate for different objects, and that the framework can be easily adapted across different underactuated hand models. In the end, we evaluated our planning and control algorithm with handwriting tasks, and demonstrated the effectiveness of the proposed framework.

show abstract

Contingent Contact-Based Motion Planning

Cited by 25 publications

References 24 publications

A Survey of Robot Manipulation in Contact

A Survey of Robot Manipulation in Contact

Robust navigation of a soft growing robot by exploiting contact with the environment

Hand–object configuration estimation using particle filters for dexterous in-hand manipulation

Contact Info

Product

Resources

About