FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385301318> ?p ?o ?g. }

• W4385301318 abstract "Autonomous driving and its widespread adoption have long held tremendous promise. Nevertheless, without a trustworthy and thorough testing procedure, not only does the industry struggle to mass-produce autonomous vehicles (AV), but neither the general public nor policymakers are convinced to accept the innovations. Generating safety-critical scenarios that present significant challenges to AV is an essential first step in testing. Real-world datasets include naturalistic but overly safe driving behaviors, whereas simulation would allow for unrestricted exploration of diverse and aggressive traffic scenarios. Conversely, higher-dimensional searching space in simulation disables efficient scenario generation without real-world data distribution as implicit constraints. In order to marry the benefits of both, it seems appealing to learn to generate scenarios from both offline real-world and online simulation data simultaneously. Therefore, we tailor a Reversely Regularized Hybrid Offline-and-Online ((Re) <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> H2O) Reinforcement Learning recipe to additionally penalize Q-values on real-world data and reward Q-values on simulated data, which ensures the generated scenarios are both varied and adversarial. Through extensive experiments, our solution proves to produce more risky scenarios than competitive baselines and it can generalize to work with various autonomous driving models. In addition, these generated scenarios are also corroborated to be capable of fine-tuning AV performance." @default.
• W4385301318 created "2023-07-28" @default.
• W4385301318 creator A5019557411 @default.
• W4385301318 creator A5019886356 @default.
• W4385301318 creator A5025327730 @default.
• W4385301318 creator A5025495733 @default.
• W4385301318 creator A5039604422 @default.
• W4385301318 creator A5044544424 @default.
• W4385301318 creator A5069540304 @default.
• W4385301318 date "2023-06-04" @default.
• W4385301318 modified "2023-09-26" @default.
• W4385301318 title "(Re)²H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learning" @default.
• W4385301318 cites W1895727713 @default.
• W4385301318 cites W1948031799 @default.
• W4385301318 cites W2008039411 @default.
• W4385301318 cites W2521921275 @default.
• W4385301318 cites W2525936901 @default.
• W4385301318 cites W2538971299 @default.
• W4385301318 cites W2561003639 @default.
• W4385301318 cites W2755725656 @default.
• W4385301318 cites W2797143217 @default.
• W4385301318 cites W2889790565 @default.
• W4385301318 cites W2891056855 @default.
• W4385301318 cites W2896642734 @default.
• W4385301318 cites W2897535010 @default.
• W4385301318 cites W2923088732 @default.
• W4385301318 cites W2943847575 @default.
• W4385301318 cites W2963184890 @default.
• W4385301318 cites W2963657083 @default.
• W4385301318 cites W2965888130 @default.
• W4385301318 cites W2968176166 @default.
• W4385301318 cites W2970679500 @default.
• W4385301318 cites W2989798627 @default.
• W4385301318 cites W2989981704 @default.
• W4385301318 cites W2991158008 @default.
• W4385301318 cites W3032950445 @default.
• W4385301318 cites W3034264193 @default.
• W4385301318 cites W3098023203 @default.
• W4385301318 cites W3103733072 @default.
• W4385301318 cites W3112716182 @default.
• W4385301318 cites W3116444130 @default.
• W4385301318 cites W3127647470 @default.
• W4385301318 cites W3130718496 @default.
• W4385301318 cites W3130864471 @default.
• W4385301318 cites W3133465684 @default.
• W4385301318 cites W3138145312 @default.
• W4385301318 cites W3175727500 @default.
• W4385301318 cites W3179442871 @default.
• W4385301318 cites W3179903080 @default.
• W4385301318 cites W3181350748 @default.
• W4385301318 cites W3184178129 @default.
• W4385301318 cites W3196020871 @default.
• W4385301318 cites W3209351137 @default.
• W4385301318 cites W4312406013 @default.
• W4385301318 doi "https://doi.org/10.1109/iv55152.2023.10186559" @default.
• W4385301318 hasPublicationYear "2023" @default.
• W4385301318 type Work @default.
• W4385301318 citedByCount "0" @default.
• W4385301318 crossrefType "proceedings-article" @default.
• W4385301318 hasAuthorship W4385301318A5019557411 @default.
• W4385301318 hasAuthorship W4385301318A5019886356 @default.
• W4385301318 hasAuthorship W4385301318A5025327730 @default.
• W4385301318 hasAuthorship W4385301318A5025495733 @default.
• W4385301318 hasAuthorship W4385301318A5039604422 @default.
• W4385301318 hasAuthorship W4385301318A5044544424 @default.
• W4385301318 hasAuthorship W4385301318A5069540304 @default.
• W4385301318 hasBestOaLocation W43853013182 @default.
• W4385301318 hasConcept C119857082 @default.
• W4385301318 hasConcept C153701036 @default.
• W4385301318 hasConcept C154945302 @default.
• W4385301318 hasConcept C160920958 @default.
• W4385301318 hasConcept C37736160 @default.
• W4385301318 hasConcept C38652104 @default.
• W4385301318 hasConcept C41008148 @default.
• W4385301318 hasConcept C97541855 @default.
• W4385301318 hasConceptScore W4385301318C119857082 @default.
• W4385301318 hasConceptScore W4385301318C153701036 @default.
• W4385301318 hasConceptScore W4385301318C154945302 @default.
• W4385301318 hasConceptScore W4385301318C160920958 @default.
• W4385301318 hasConceptScore W4385301318C37736160 @default.
• W4385301318 hasConceptScore W4385301318C38652104 @default.
• W4385301318 hasConceptScore W4385301318C41008148 @default.
• W4385301318 hasConceptScore W4385301318C97541855 @default.
• W4385301318 hasFunder F4320321001 @default.
• W4385301318 hasLocation W43853013181 @default.
• W4385301318 hasLocation W43853013182 @default.
• W4385301318 hasOpenAccess W4385301318 @default.
• W4385301318 hasPrimaryLocation W43853013181 @default.
• W4385301318 hasRelatedWork W2897573479 @default.
• W4385301318 hasRelatedWork W2955689724 @default.
• W4385301318 hasRelatedWork W2964108292 @default.
• W4385301318 hasRelatedWork W3013360982 @default.
• W4385301318 hasRelatedWork W3101326751 @default.
• W4385301318 hasRelatedWork W3145910327 @default.
• W4385301318 hasRelatedWork W4280599367 @default.
• W4385301318 hasRelatedWork W4281255644 @default.
• W4385301318 hasRelatedWork W4287598984 @default.
• W4385301318 hasRelatedWork W4319083788 @default.
• W4385301318 isParatext "false" @default.
• W4385301318 isRetracted "false" @default.

• next