SACBP: Belief space planning for continuous-time dynamical systems via stochastic sequential action control

Nishimura, Haruki; Schwager, Mac

doi:10.1177/02783649211037697

Cited by 12 publications

(17 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose an effective solution to this problem via risk-sensitive stochastic optimal control, wherein desired collision avoidance and goal reaching motion is achieved by a cost function, a risk-sensitivity parameter, and dynamic optimization. Specifically, we extend the Stochastic Sequential Action Control (SAC) algorithm [1] to a risk-sensitive setting through the use of exponential disutility [2], the objective often referred to as the entropic risk measure [3]. The proposed sampling-based algorithm, which we name Risk-Sensitive Sequential Action Control (RSSAC), is a stochastic nonlinear model predictive control (NMPC) algorithm that optimally improves upon a given nominal control with a series of control perturbations.…”

Section: Introductionmentioning

confidence: 99%

Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction

Nishimura

Ivanovic

Gaidon

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

This paper presents a novel online framework for safe crowd-robot interaction based on risk-sensitive stochastic optimal control, wherein the risk is modeled by the entropic risk measure. The sampling-based model predictive control relies on mode insertion gradient optimization for this risk measure as well as Trajectron++, a state-of-the-art generative model that produces multimodal probabilistic trajectory forecasts for multiple interacting agents. Our modular approach decouples the crowd-robot interaction into learning-based prediction and model-based control, which is advantageous compared to endto-end policy learning methods in that it allows the robot's desired behavior to be specified at run time. In particular, we show that the robot exhibits diverse interaction behavior by varying the risk sensitivity parameter. A simulation study and a real-world experiment show that the proposed online framework can accomplish safe and efficient navigation while avoiding collisions with more than 50 humans in the scene.

show abstract

Section: Introductionmentioning

confidence: 99%

Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction

Nishimura

Ivanovic

Gaidon

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Informative Path Planning: Our work is close in both spirit and motivation to information-gathering behaviours in path planning [2,4,6,26,27,28]. Most existing methods in this category need to estimate the surrounding map while executing variants of frontier-based exploration.…”

Section: Background and Related Workmentioning

confidence: 97%

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Manderson¹,

Higuera²,

Wapnick³

et al. 2020

Robotics: Science and Systems XVI

View full text Add to dashboard Cite

We present Nav2Goal, a data-efficient and end-toend learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided by a user without any prior map, all while avoiding obstacles and choosing paths that cover user-informed regions of interest. Our approach is based on recent advances in conditional imitation learning. General-purpose safe and informative actions are demonstrated by a human expert. The learned policy is subsequently extended to be goal-conditioned by training with hindsight relabelling, guided by the robot's relative localization system, which requires no additional manual annotation. We deployed our method on an underwater vehicle in the open ocean to collect scientifically relevant data of coral reefs, which allowed our robot to operate safely and autonomously, even at very close proximity to the coral. Our field deployments have demonstrated over a kilometer of autonomous visual navigation, where the robot reaches on the order of 40 waypoints, while collecting scientifically relevant data. This is done while travelling within 0.5 m altitude from sensitive corals and exhibiting significant learned agility to overcome turbulent ocean conditions and to actively avoid collisions.

show abstract

“…Another approach can model the motion of the target to be a random walk, especially when there is no prior information about the mobility of the target [10], [11]. The mobility is modeled by a 2D Brownian motion in [12] where the target can move within a bounded region.…”

Section: Active Target Trackingmentioning

confidence: 99%

“…We next analyze the localization performance when the targets are moving locally in a contained area. The target movement is modeled by a 2D Brownian motion with a covariance of 0.1I 2 , similar to the setting in [12]. Our current formulation of the uncertainty histogram does not allow tracking targets performing large displacements.…”

Section: Localizing Dynamic Targetsmentioning

confidence: 99%

Active Localization of Multiple Targets from Noisy Relative Measurements

Engin

Isler

2021

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

Consider a mobile robot tasked with localizing targets at unknown locations by obtaining relative measurements. The observations can be bearing or range measurements. How should the robot move so as to localize the targets and minimize the uncertainty in their locations as quickly as possible? Most existing approaches are either greedy in nature or rely on accurate initial estimates.We formulate this path planning problem as an unsupervised learning problem where the measurements are aggregated using a Bayesian histogram filter. The robot learns to minimize the total uncertainty of each target in the shortest amount of time using the current measurement and an aggregate representation of the current belief state. We analyze our method in a series of experiments where we show that our method outperforms a standard greedy approach. In addition, its performance is also comparable to an offline algorithm which has access to the true location of the targets.

show abstract

SACBP: Belief space planning for continuous-time dynamical systems via stochastic sequential action control

Cited by 12 publications

References 42 publications

Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction

Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Active Localization of Multiple Targets from Noisy Relative Measurements

Contact Info

Product

Resources

About