Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213697024> ?p ?o ?g. }
- W3213697024 abstract "Accurate trajectory prediction of vehicles is essential for reliable autonomous driving. To maintain consistent performance as a vehicle driving around different cities, it is crucial to adapt to changing traffic circumstances and achieve lifelong trajectory prediction model. To realize it, catastrophic forgetting is a main problem to be addressed. In this paper, a divergence measurement method based on conditional Kullback-Leibler divergence is proposed first to evaluate spatiotemporal dependency difference among varied driving circumstances. Then based on generative replay, a novel lifelong vehicle trajectory prediction framework is developed. The framework consists of a conditional generation model and a vehicle trajectory prediction model. The conditional generation model is a generative adversarial network conditioned on position configuration of vehicles. After learning and merging trajectory distribution of vehicles across different cities, the generation model replays trajectories with prior samplings as inputs, which alleviates catastrophic forgetting. The vehicle trajectory prediction model is trained by the replayed trajectories and achieves consistent prediction performance on visited cities. A lifelong experiment setup is established on four open datasets including five tasks. Spatiotemporal dependency divergence is calculated for different tasks. Even though these divergence, the proposed framework exhibits lifelong learning ability and achieves consistent performance on all tasks." @default.
- W3213697024 created "2021-11-22" @default.
- W3213697024 creator A5027716759 @default.
- W3213697024 creator A5062133020 @default.
- W3213697024 creator A5063512998 @default.
- W3213697024 creator A5071343023 @default.
- W3213697024 creator A5083722247 @default.
- W3213697024 date "2021-11-14" @default.
- W3213697024 modified "2023-09-23" @default.
- W3213697024 title "Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay" @default.
- W3213697024 cites W1522301498 @default.
- W3213697024 cites W1579853615 @default.
- W3213697024 cites W1710476689 @default.
- W3213697024 cites W1895577753 @default.
- W3213697024 cites W1905882502 @default.
- W3213697024 cites W1983026501 @default.
- W3213697024 cites W2012849708 @default.
- W3213697024 cites W2033178790 @default.
- W3213697024 cites W2048093873 @default.
- W3213697024 cites W2057587543 @default.
- W3213697024 cites W2068952833 @default.
- W3213697024 cites W2077933344 @default.
- W3213697024 cites W2099111195 @default.
- W3213697024 cites W2105242877 @default.
- W3213697024 cites W2109322262 @default.
- W3213697024 cites W2125865219 @default.
- W3213697024 cites W2131762276 @default.
- W3213697024 cites W2136144249 @default.
- W3213697024 cites W2151573792 @default.
- W3213697024 cites W2153323685 @default.
- W3213697024 cites W2155010204 @default.
- W3213697024 cites W2281287867 @default.
- W3213697024 cites W2424778531 @default.
- W3213697024 cites W2473930607 @default.
- W3213697024 cites W2494980014 @default.
- W3213697024 cites W2508809738 @default.
- W3213697024 cites W2554616628 @default.
- W3213697024 cites W2560647685 @default.
- W3213697024 cites W2577946330 @default.
- W3213697024 cites W2580495915 @default.
- W3213697024 cites W2583761661 @default.
- W3213697024 cites W2618767506 @default.
- W3213697024 cites W2734314755 @default.
- W3213697024 cites W2763916687 @default.
- W3213697024 cites W2765895026 @default.
- W3213697024 cites W2784715585 @default.
- W3213697024 cites W2803832867 @default.
- W3213697024 cites W2883602772 @default.
- W3213697024 cites W2892234010 @default.
- W3213697024 cites W2894094671 @default.
- W3213697024 cites W2895723011 @default.
- W3213697024 cites W2896642734 @default.
- W3213697024 cites W2947530128 @default.
- W3213697024 cites W2949767467 @default.
- W3213697024 cites W2962707369 @default.
- W3213697024 cites W2963001155 @default.
- W3213697024 cites W2963588172 @default.
- W3213697024 cites W2963906196 @default.
- W3213697024 cites W2964151081 @default.
- W3213697024 cites W2964189064 @default.
- W3213697024 cites W2965316269 @default.
- W3213697024 cites W2966682689 @default.
- W3213697024 cites W2967835402 @default.
- W3213697024 cites W2970971581 @default.
- W3213697024 cites W2974990249 @default.
- W3213697024 cites W2975767248 @default.
- W3213697024 cites W2978098801 @default.
- W3213697024 cites W2980087597 @default.
- W3213697024 cites W2987583674 @default.
- W3213697024 cites W2989851631 @default.
- W3213697024 cites W2995139074 @default.
- W3213697024 cites W2995962413 @default.
- W3213697024 cites W3030364939 @default.
- W3213697024 cites W3037376004 @default.
- W3213697024 cites W3048295731 @default.
- W3213697024 cites W3103346379 @default.
- W3213697024 cites W3103724573 @default.
- W3213697024 cites W3125468173 @default.
- W3213697024 cites W3135431857 @default.
- W3213697024 cites W3137750826 @default.
- W3213697024 cites W3202122424 @default.
- W3213697024 cites W3210952262 @default.
- W3213697024 doi "https://doi.org/10.48550/arxiv.2111.07511" @default.
- W3213697024 hasPublicationYear "2021" @default.
- W3213697024 type Work @default.
- W3213697024 sameAs 3213697024 @default.
- W3213697024 citedByCount "0" @default.
- W3213697024 crossrefType "posted-content" @default.
- W3213697024 hasAuthorship W3213697024A5027716759 @default.
- W3213697024 hasAuthorship W3213697024A5062133020 @default.
- W3213697024 hasAuthorship W3213697024A5063512998 @default.
- W3213697024 hasAuthorship W3213697024A5071343023 @default.
- W3213697024 hasAuthorship W3213697024A5083722247 @default.
- W3213697024 hasBestOaLocation W32136970241 @default.
- W3213697024 hasConcept C10138342 @default.
- W3213697024 hasConcept C108771440 @default.
- W3213697024 hasConcept C119857082 @default.
- W3213697024 hasConcept C121332964 @default.
- W3213697024 hasConcept C1276947 @default.
- W3213697024 hasConcept C13662910 @default.