Ethical Planning with Multiple Temporal Values

Parker, Timothy; Grandi, Umberto; Lorini, Emiliano; Clodic, Aurélie; Alami, Rachid

doi:10.3233/faia220644

Cited by 2 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The set of γ-compatible histories is noted Hist (γ). A formal definition can be found in the full version of the paper [20].…”

Section: Multi-agent Action Theorymentioning

confidence: 99%

“…In the interest of space we have omitted or sketched the proofs of our results, which can be found in the full version of this paper [20].…”

Section: Formalising Responsibilitymentioning

confidence: 99%

“…This is because we need to find start state and a plan for all agents besides A1 such that the intended plan for A1 leads to ω but there exists some other plan for A1 that leads to ¬ω. This can be solved in a single planning problem (at least, one problem per possible start state) by creating a duplicate copy of each object, allowing us to effectively run two copies of the planning domain 3 We do not define do(i, a, t) here as its definition is quite complex and straightforward, it can be found in the full version of the paper [20].…”

Section: Pddl Implementationmentioning

confidence: 99%

“…In this section we will demonstrate the computational complexity of determining various kinds of responsibility. Full proofs of our results can be found in the full version of this paper [20]. We define X-ATTRIBUTION as the problem of determining if i bears X∈ {CAR,CPR,CCR,AAR} for ω in Π and X-ANTICIPATION as the problem of determining if i anticipates X for ω in Π. Theorem 6.…”

Section: Complexity Analysismentioning

confidence: 99%

See 3 more Smart Citations

Anticipating Responsibility in Multiagent Planning

Parker,

Grandi,

Lorini

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Responsibility anticipation is the process of determining if the actions of an individual agent may cause it to be responsible for a particular outcome. This can be used in a multi-agent planning setting to allow agents to anticipate responsibility in the plans they consider. The planning setting in this paper includes partial information regarding the initial state and considers formulas in linear temporal logic as positive or negative outcomes to be attained or avoided. We firstly define attribution for notions of active, passive and contributive responsibility, and consider their agentive variants. We then use these to define the notion of responsibility anticipation. We prove that our notions of anticipated responsibility can be used to coordinate agents in a planning setting and give complexity results for our model, discussing equivalence with classical planning. We also present an outline for solving some of our attribution and anticipation problems using PDDL solvers.

show abstract

“…The set of γ-compatible histories is noted Hist (γ). A formal definition can be found in the full version of the paper [20].…”

Section: Multi-agent Action Theorymentioning

confidence: 99%

“…In the interest of space we have omitted or sketched the proofs of our results, which can be found in the full version of this paper [20].…”

Section: Formalising Responsibilitymentioning

confidence: 99%

Section: Pddl Implementationmentioning

confidence: 99%

Section: Complexity Analysismentioning

confidence: 99%

See 2 more Smart Citations

Anticipating Responsibility in Multiagent Planning

Parker,

Grandi,

Lorini

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

Finding middle grounds for incoherent horn expressions: the moral machine case

Ozaki,

Rehman,

Slavkovik

2024

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

Smart devices that operate in a shared environment with people need to be aligned with their values and requirements. We study the problem of multiple stakeholders informing the same device on what the right thing to do is. Specifically, we focus on how to reach a middle ground among the stakeholders inevitably incoherent judgments on what the rules of conduct for the device should be. We formally define a notion of middle ground and discuss the main properties of this notion. Then, we identify three sufficient conditions on the class of Horn expressions for which middle grounds are guaranteed to exist. We provide a polynomial time algorithm that computes middle grounds, under these conditions. We also show that if any of the three conditions is removed then middle grounds for the resulting (larger) class may not exist. Finally, we implement our algorithm and perform experiments using data from the Moral Machine Experiment. We present conflicting rules for different countries and how the algorithm finds the middle ground in this case.

show abstract

Ethical Planning with Multiple Temporal Values

Abstract: This paper describes an approach to ethical planning in robotics that combines classical planning, Linear Temporal Logic and lexicographically ordered value sets. We also discuss the features and limitations of the model, with particular attention to its philosophical implications.

Cited by 2 publications

References 24 publications

Anticipating Responsibility in Multiagent Planning

Anticipating Responsibility in Multiagent Planning

Finding middle grounds for incoherent horn expressions: the moral machine case

Contact Info

Product

Resources

About