A Framework for Online Updates to Safe Sets for Uncertain Dynamics

Shih, Jennifer C.; Meier, Franziska; Rai, Akshara

doi:10.1109/iros45743.2020.9341606

Cited by 7 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to infer the safety of a robot is to build a safe set through Hamilton-J, but because of the long computation time, it sometimes assumes perfect knowledge of the mechanics, and the safety set is calculated offline. Shih et al [340] proposed a new framework for learning safety control policies from simulation and using it to generate online safety sets from uncertain dynamics. As climate change increases the frequency and severity of natural disasters, response organizations need improved data to better understand the dynamics of disaster impacts.…”

Section: ) Metaverse Applicationsmentioning

confidence: 99%

A Metaverse: Taxonomy, Components, Applications, and Open Challenges

2022

View full text Add to dashboard Cite

Unlike previous studies on the Metaverse based on Second Life, the current Metaverse is based on the social value of Generation Z that online and offline selves are not different. With the technological development of deep learning-based high-precision recognition models and natural generation models, Metaverse is being strengthened with various factors, from mobile-based always-on access to connectivity with reality using virtual currency. The integration of enhanced social activities and neural-net methods requires a new definition of Metaverse suitable for the present, different from the previous Metaverse. This paper divides the concepts and essential techniques necessary for realizing the Metaverse into three components (i.e., hardware, software, and contents) and three approaches (i.e., user interaction, implementation, and application) rather than marketing or hardware approach to conduct a comprehensive analysis. Furthermore, we describe essential methods based on three components and techniques to Metaverse's representative Ready Player One, Roblox, and Facebook research in the domain of films, games, and studies. Finally, we summarize the limitations and directions for implementing the immersive Metaverse as social influences, constraints, and open challenges.

show abstract

Section: ) Metaverse Applicationsmentioning

confidence: 99%

A Metaverse: Taxonomy, Components, Applications, and Open Challenges

2022

View full text Add to dashboard Cite

show abstract

“…However, this approach is often too computationally demanding to be run online for complex systems. To ease the computational burden, constraints are often only enforced on trajectories of finite horizon, such as in sequential trajectory planning [4], [5] and model-predictive control [1], [6]. Since these methods only enforce constraints along partial trajectories, guaranteeing safety requires additional conditions to be met.…”

Section: A Related Workmentioning

confidence: 99%

“…This has motivated the interest in learning or refining these objects from data [14]- [16]. A novel approach aims at opening up the toolbox of reinforcement learning (RL) for the computation of reachable sets [5], [17]. In the usual case where the optimal behavior is also learned from data, however, a competition arises between exploring for safety and for optimality.…”

Section: A Related Workmentioning

confidence: 99%

“…1) Hamilton-Jacobi Reachability: The goal of HJ reachability is to find the set of states from where the system can be robustly driven into a target set, which is called the backrechable tube of the target set [7]. The main method is to cast this as an optimal control problem and find a value function defined as in Equation (5), where the reward is the signed distance to the target set, and is not discounted (i.e., τ = ∞). This value function satisfies, in a broad sense, the Hamilton-Jacobi-Bellman partial differential equation (HJB PDE), which is a local version of the dynamic programming identity (see Equation ( 6)).…”

Section: A the Viability Kernel As A Level Setmentioning

confidence: 99%

See 1 more Smart Citation

Safe Value Functions

Massiani¹,

Heim²,

Solowjow³

et al. 2021

Preprint

View full text Add to dashboard Cite

The relationship between safety and optimality in control is not well understood, and they are often seen as important yet conflicting objectives. There is a pressing need to formalize this relationship, especially given the growing prominence of learning-based methods. Indeed, it is common practice in reinforcement learning to simply modify reward functions by penalizing failures, with the penalty treated as a mere heuristic. We rigorously examine this relationship, and formalize the requirements for safe value functions: value functions that are both optimal for a given task, and enforce safety. We reveal the structure of this relationship through a proof of strong duality, showing that there always exists a finite penalty that induces a safe value function. This penalty is not unique, but upperunbounded: larger penalties do not harm optimality. Although it is often not possible to compute the minimum required penalty, we reveal clear structure of how the penalty, rewards, discount factor, and dynamics interact. This insight suggests practical, theory-guided heuristics to design reward functions for control problems where safety is important.

show abstract

“…A similar least-restrictive safe control strategy based on reachability can be adopted for single agent systems that aim to avoid dangerous regions in the environment while disturbance is present. This enables a least-restrictive control strategy where an agent gets to execute any type of controller such as a goal controller that gets the vehicle to its target [22], [23] or a machine learning-based controller [27], [28] when the agent is not at the boundary of a backward reachable set.…”

Section: B Least-restrictive Safe Control Strategiesmentioning

confidence: 99%

Learning-based Initialization Strategy for Safety of Multi-Vehicle Systems

Shih¹,

Rai²,

Ghaoui³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-vehicle collision avoidance is a highly crucial problem due to the soaring interests of introducing autonomous vehicles into the real world in recent years. The safety of these vehicles while they complete their objectives is of paramount importance. Hamilton-Jacobi (HJ) reachability is a promising tool for guaranteeing safety for low-dimensional systems. However, due to its exponential complexity in computation time, no reachability-based methods have been able to guarantee safety for more than three vehicles successfully in unstructured scenarios. For systems with four or more vehicles, we can only empirically validate their safety performance. While reachability-based safety methods enjoy a flexible leastrestrictive control strategy, it is challenging to reason about long-horizon trajectories online because safety at any given state is determined by looking up its safety value in a precomputed table that does not exhibit favorable properties that continuous functions have. This motivates the problem of improving the safety performance of unstructured multi-vehicle systems when safety cannot be guaranteed given any leastrestrictive safety-aware collision avoidance algorithm while avoiding online trajectory optimization. In this paper, we propose a novel approach using supervised learning to enhance the safety of vehicles by proposing new initial states in very close neighborhood of the original initial states of vehicles. Our experiments demonstrate the effectiveness of our proposed approach and show that vehicles are able to get to their goals with better safety performance with our approach compared to a baseline approach in wide-ranging scenarios.

show abstract

A Framework for Online Updates to Safe Sets for Uncertain Dynamics

Cited by 7 publications

References 16 publications

A Metaverse: Taxonomy, Components, Applications, and Open Challenges

A Metaverse: Taxonomy, Components, Applications, and Open Challenges

Safe Value Functions

Learning-based Initialization Strategy for Safety of Multi-Vehicle Systems

Contact Info

Product

Resources

About