Provably Safe and Efficient Motion Planning with Uncertain Human Dynamics

Shen, Li; Figueroa, Nadia; Shah, Ankit; Shah, Julie A.

doi:10.15607/rss.2021.xvii.050

Cited by 16 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Empirically, GP-ZKF outperformed the stochastic baselines (GP-EKF, GP-UKF, and GP-PF [7]) in both a simulated pendulum and real-world dressing domain. Future work will focus on combining our approach with control methods [28], [29], as well as richer and more computationally scalable models for force-based estimation.…”

Section: Discussionmentioning

confidence: 99%

Set-Based State Estimation With Probabilistic Consistency Guarantee Under Epistemic Uncertainty

Shen

Stouraitis

Gienger

et al. 2022

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Consistent state estimation is challenging, especially under the epistemic uncertainties arising from learned (nonlinear) dynamic and observation models. In this work, we propose a set-based estimation algorithm, named Gaussian Process-Zonotopic Kalman Filter (GP-ZKF), that produces zonotopic state estimates while respecting both the epistemic uncertainties in the learned models and aleatoric uncertainties. Our method guarantees probabilistic consistency, in the sense that the true states are bounded by sets (zonotopes) across all time steps, with high probability. We formally relate GP-ZKF with the corresponding stochastic approach, GP-EKF, in the case of learned (nonlinear) models. In particular, when linearization errors and aleatoric uncertainties are omitted and epistemic uncertainties are simplified, GP-ZKF reduces to GP-EKF. We empirically demonstrate our method's efficacy in both a simulated pendulum domain and a real-world robot-assisted dressing domain, where GP-ZKF produced more consistent and less conservative setbased estimates than all baseline stochastic methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Set-Based State Estimation With Probabilistic Consistency Guarantee Under Epistemic Uncertainty

Shen

Stouraitis

Gienger

et al. 2022

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The dressing assistance is a primary task that occurs everyday in elderly care, and has been considered in previous assistive robot research. Recently the authors of [25] address the problem from safety perspective and proposed a motion planning strategy that theoretically guarantees safety under the uncertainty in human dynamic models. Zhang et al, uses a hybrid force/position control with simple planning for dressing [26], while [27] use deep reinforcement learning (DRL) to simultaneously train human and robot control policies as separate neural networks using physics simulations.…”

Section: Robotic Experimentsmentioning

confidence: 99%

Learning Task-Parameterized Skills From Few Demonstrations

Zhu

Gienger

Kober

2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Moving away from repetitive tasks, robots nowadays demand versatile skills that adapt to different situations. Taskparameterized learning improves the generalization of motion policies by encoding relevant contextual information in the task parameters, hence enabling flexible task executions. However, training such a policy often requires collecting multiple demonstrations in different situations. To comprehensively create different situations is non-trivial thus renders the method less applicable to real-world problems. Therefore, training with fewer demonstrations/situations is desirable. This paper presents a novel concept to augment the original training dataset with synthetic data for policy improvements, thus allows learning task-parameterized skills with few demonstrations.

show abstract

“…Many approaches in deformable object manipulation are limited to specific scenarios due to the complexity of real hardware setups [7]- [12]. Furthermore, there is a lack of easily tunable yet realistic simulators that support deformables and could aid experimentation with novel tasks.…”

Section: Background a Real-to-sim For Deformable Objectsmentioning

confidence: 99%

DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objects

Sundaresan¹,

Antonova²,

Bohg³

2022

Preprint

View full text Add to dashboard Cite

Research in manipulation of deformable objects is typically conducted on a limited range of scenarios, because handling each scenario on hardware takes significant effort. Realistic simulators with support for various types of deformations and interactions have the potential to speed up experimentation with novel tasks and algorithms. However, for highly deformable objects it is challenging to align the output of a simulator with the behavior of real objects. Manual tuning is not intuitive, hence automated methods are needed. We view this alignment problem as a joint perception-inference challenge and demonstrate how to use recent neural network architectures to successfully perform simulation parameter inference from real point clouds. We analyze the performance of various architectures, comparing their data and training requirements. Furthermore, we propose to leverage differentiable point cloud sampling and differentiable simulation to significantly reduce the time to achieve the alignment. We employ an efficient way to propagate gradients from point clouds to simulated meshes and further through to the physical simulation parameters, such as mass and stiffness. Experiments with highly deformable objects show that our method can achieve comparable or better alignment with real object behavior, while reducing the time needed to achieve this by more than an order of magnitude. Videos and supplementary material are available at https://tinyurl.com/diffcloud.

show abstract

Provably Safe and Efficient Motion Planning with Uncertain Human Dynamics

Cited by 16 publications

References 27 publications

Set-Based State Estimation With Probabilistic Consistency Guarantee Under Epistemic Uncertainty

Set-Based State Estimation With Probabilistic Consistency Guarantee Under Epistemic Uncertainty

Learning Task-Parameterized Skills From Few Demonstrations

DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objects

Contact Info

Product

Resources

About