Variable risk control via stochastic optimization

Kuindersma, Scott; Grupen, Roderic A.; Barto, Andrew G.

doi:10.1177/0278364913476124

Cited by 35 publications

(18 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though we only considered the efficacy of the algorithm under noisy measurement of metabolic cost using single parameter optimization, Bayesian optimization is generally applicable for multi-dimensional problems [ 28 – 32 ]. This method has been successfully applied to many robotic applications such as robot gait optimization [ 60 , 61 ] and balancing recovery strategies under large disturbances [ 62 ]. In addition, another parameter selection application using a noisy physiological signal confirmed the sample efficiency of Bayesian optimization on a multi-dimensional problem during HIL optimization [ 33 ].…”

Section: Discussionmentioning

confidence: 99%

Human-in-the-loop Bayesian optimization of wearable device parameters

et al. 2017

View full text Add to dashboard Cite

The increasing capabilities of exoskeletons and powered prosthetics for walking assistance have paved the way for more sophisticated and individualized control strategies. In response to this opportunity, recent work on human-in-the-loop optimization has considered the problem of automatically tuning control parameters based on realtime physiological measurements. However, the common use of metabolic cost as a performance metric creates significant experimental challenges due to its long measurement times and low signal-to-noise ratio. We evaluate the use of Bayesian optimization—a family of sample-efficient, noise-tolerant, and global optimization methods—for quickly identifying near-optimal control parameters. To manage experimental complexity and provide comparisons against related work, we consider the task of minimizing metabolic cost by optimizing walking step frequencies in unaided human subjects. Compared to an existing approach based on gradient descent, Bayesian optimization identified a near-optimal step frequency with a faster time to convergence (12 minutes, p < 0.01), smaller inter-subject variability in convergence time (± 2 minutes, p < 0.01), and lower overall energy expenditure (p < 0.01).

show abstract

Section: Discussionmentioning

confidence: 99%

Human-in-the-loop Bayesian optimization of wearable device parameters

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In this work, we introduced an ERM cost to improve trajectory robustness as the ERM cost minimizes the sensitivity of the solutions to variations in the contact parameters ( Chen et al, 2009 ); nonetheless, we note that neither the ERM nor the chance constraints propagate uncertainty through the dynamics. Following other robust TO approaches, an alternative to our work would be to sample the uncertain contact models and then minimize either the expected cost ( Dai and Tedrake, 2012 ; Kuindersma et al, 2013 ; Mordatch et al, 2015 ) or an expected exponential transformation of the cost ( Jacobson, 1973 ; Farshidian and Buchli, 2015 ; Ponton et al, 2018 ), taking the expectation numerically over an ensemble of trajectories. However, developing an ensemble approach to contact-robust optimization is not without its challenges.…”

Section: Discussionmentioning

confidence: 99%

Mediating Between Contact Feasibility and Robustness of Trajectory Optimization Through Chance Complementarity Constraints

2022

View full text Add to dashboard Cite

As robots move from the laboratory into the real world, motion planning will need to account for model uncertainty and risk. For robot motions involving intermittent contact, planning for uncertainty in contact is especially important, as failure to successfully make and maintain contact can be catastrophic. Here, we model uncertainty in terrain geometry and friction characteristics, and combine a risk-sensitive objective with chance constraints to provide a trade-off between robustness to uncertainty and constraint satisfaction with an arbitrarily high feasibility guarantee. We evaluate our approach in two simple examples: a push-block system for benchmarking and a single-legged hopper. We demonstrate that chance constraints alone produce trajectories similar to those produced using strict complementarity constraints; however, when equipped with a robust objective, we show the chance constraints can mediate a trade-off between robustness to uncertainty and strict constraint satisfaction. Thus, our study may represent an important step towards reasoning about contact uncertainty in motion planning.

show abstract

“…However, there are many examples of popular risk metrics that do not fulfill the axioms we advocate. For example, a very popular metric to quantify risk in robotics applications is the mean-variance risk metric: E[Z] + β Variance[Z] (see, e.g., [18,13,21]). The mean-variance metric satisfies A6 but fails to satisfy the other axioms.…”

Section: Examples and Pitfalls Of Commonly Used Risk Metricsmentioning

confidence: 99%

How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics

Majumdar

Pavone

2019

Springer Proceedings in Advanced Robotics

155

145

View full text Add to dashboard Cite

Endowing robots with the capability of assessing risk and making riskaware decisions is widely considered a key step toward ensuring safety for robots operating under uncertainty. But, how should a robot quantify risk? A natural and common approach is to consider the framework whereby costs are assigned to stochastic outcomes-an assignment captured by a cost random variable. Quantifying risk then corresponds to evaluating a risk metric, i.e., a mapping from the cost random variable to a real number. Yet, the question of what constitutes a "good" risk metric has received little attention within the robotics community. The goal of this paper is to explore and partially address this question by advocating axioms that risk metrics in robotics applications should satisfy in order to be employed as rational assessments of risk. We discuss general representation theorems that precisely characterize the class of metrics that satisfy these axioms (referred to as distortion risk metrics), and provide instantiations that can be used in applications. We further discuss pitfalls of commonly used risk metrics in robotics, and discuss additional properties that one must consider in sequential decision making tasks. Our hope is that the ideas presented here will lead to a foundational framework for quantifying risk (and hence safety) in robotics applications.

show abstract

Variable risk control via stochastic optimization

Cited by 35 publications

References 53 publications

Human-in-the-loop Bayesian optimization of wearable device parameters

Human-in-the-loop Bayesian optimization of wearable device parameters

Mediating Between Contact Feasibility and Robustness of Trajectory Optimization Through Chance Complementarity Constraints

How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics

Contact Info

Product

Resources

About