The manifold particle filter for state estimation on high-dimensional implicit manifolds

Koval, Michael C.; Klingensmith, Matthew; Srinivasa, Siddhartha S.; Pollard, Nancy S.; Kaess, Michael

doi:10.1109/icra.2017.7989543

Cited by 22 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, in many cases, the sensors are bulky, or the objects considered are planar or consist of simple geometries. Finally, some works explore how to combine multiple tactile readings and reason in the space of contact manifolds [16,17]. However, these are still based on low-resolution tactile feedback, often a binary contact/no-contact signal, and require many tactile readings to narrow pose estimates.…”

Section: Related Workmentioning

confidence: 99%

Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering

Bauza,

Valls,

Lim

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper, we present an approach to tactile pose estimation from the first touch for known objects. First, we create an object-agnostic map from real tactile observations to contact shapes. Next, for a new object with known geometry, we learn a tailored perception model completely in simulation. To do so, we simulate the contact shapes that a dense set of object poses would produce on the sensor. Then, given a new contact shape obtained from the sensor output, we match it against the pre-computed set using the object-specific embedding learned purely in simulation using contrastive learning. This results in a perception model that can localize objects from a single tactile observation. It also allows reasoning over pose distributions and including additional pose constraints coming from other perception systems or multiple contacts. We provide quantitative results for four objects. Our approach provides high accuracy pose estimations from distinctive tactile observations while regressing pose distributions to account for those contact shapes that could result from different object poses. We further extend and test our approach in multi-contact scenarios where several tactile sensors are simultaneously in contact with the object. Website: mcube.mit.edu/research/tactile_loc_first_touch.html

show abstract

Section: Related Workmentioning

confidence: 99%

Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering

Bauza,

Valls,

Lim

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Other more task-specific algorithms also relevant to GP-SUM are the multihypothesis tracking filter (MHT) [19] and the manifold particle filter (MPF) [20]. MHT is designed to solve a data association problem for multiple target tracking by representing the joint distribution of the targets as a Gaussian mixture.…”

Section: Related Workmentioning

confidence: 99%

GP-SUM. Gaussian Process Filtering of non-Gaussian Beliefs

Bauzá

Rodríguez

2020

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

This work studies the problem of stochastic dynamic filtering and state propagation with complex beliefs. The main contribution is GP-SUM, a filtering algorithm tailored to dynamic systems and observation models expressed as Gaussian Processes (GP), and to states represented as a weighted Sum of Gaussians. The key attribute of GP-SUM is that it does not rely on linearizations of the dynamic or observation models, or on unimodal Gaussian approximations of the belief, hence enables tracking complex state distributions. The algorithm can be seen as a combination of a sampling-based filter with a probabilistic Bayes filter. On the one hand, GP-SUM operates by sampling the state distribution and propagating each sample through the dynamic system and observation models. On the other hand, it achieves effective sampling and accurate probabilistic propagation by relying on the GP form of the system, and the sum-of-Gaussian form of the belief. We show that GP-SUM outperforms several GP-Bayes and Particle Filters on a standard benchmark. We also demonstrate its use in a pushing task, predicting with experimental accuracy the naturally occurring non-Gaussian distributions.

show abstract

“…Calibration using physical constraints. The next family of approaches exploits physical contacts of the end effector with the environment, such as fixing the end effector to the ground [19] or using more complex setups [20][21][22]. Some form of force sensing on the part of the manipulator is required.…”

Section: Related Workmentioning

confidence: 99%

Automatic self-contained calibration of an industrial dual-arm robot with cameras using self-contact, planar constraints, and self-observation

Stepanova,

Rozlivek,

Puciow

et al. 2020

Preprint

View full text Add to dashboard Cite

We present a robot kinematic calibration method that combines complementary calibration approaches: self-contact, planar constraints, and self-observation. We analyze the estimation of the end effector parameters, joint offsets of the manipulators, calibration of the complete kinematic chain (DH parameters), and we compare our results with ground truth measurements provided by a laser tracker. Our main findings are: (1) When applying the complementary calibration approaches in isolation, the self-contact approach yields the best and most stable results. (2) All combinations of more than one approach were always superior to using any single approach in terms of calibration errors as well as the observability of the estimated parameters. Combining more approaches delivers robot parameters that better generalize to the parts of workspace not used for the calibration. (3) Sequential calibration, i.e. calibrating cameras first and then robot kinematics, is more effective than simultaneous calibration of all parameters. In real experiments, we employ two industrial manipulators mounted on a common base. The manipulators are equipped with force/torque sensors at their wrists, with two cameras attached to the robot base, and with special end effectors with fiducial markers. We collect a new comprehensive dataset for robot kinematic calibration and make it publicly available. The dataset and its analysis provide quantitative and qualitative insights that go beyond the specific manipulators used in this work and are applicable to self-contained robot kinematic calibration in general.

show abstract

The manifold particle filter for state estimation on high-dimensional implicit manifolds

Cited by 22 publications

References 30 publications

Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering

Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering

GP-SUM. Gaussian Process Filtering of non-Gaussian Beliefs

Automatic self-contained calibration of an industrial dual-arm robot with cameras using self-contact, planar constraints, and self-observation

Contact Info

Product

Resources

About