Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204161688> ?p ?o ?g. }
- W3204161688 abstract "Predicting the motion of multiple agents is necessary for planning in dynamic environments. This task is challenging for autonomous driving since agents (e.g. vehicles and pedestrians) and their associated behaviors may be diverse and influence one another. Most prior work have focused on predicting independent futures for each agent based on all past motion, and planning against these independent predictions. However, planning against independent predictions can make it challenging to represent the future interaction possibilities between different agents, leading to sub-optimal planning. In this work, we formulate a model for predicting the behavior of all agents jointly, producing consistent futures that account for interactions between agents. Inspired by recent language modeling approaches, we use a masking strategy as the query to our model, enabling one to invoke a single model to predict agent behavior in many ways, such as potentially conditioned on the goal or full future trajectory of the autonomous vehicle or the behavior of other agents in the environment. Our model architecture employs attention to combine features across road elements, agent interactions, and time steps. We evaluate our approach on autonomous driving datasets for both marginal and joint motion prediction, and achieve state of the art performance across two popular datasets. Through combining a scene-centric approach, agent permutation equivariant model, and a sequence masking strategy, we show that our model can unify a variety of motion prediction tasks from joint motion predictions to conditioned prediction." @default.
- W3204161688 created "2021-10-11" @default.
- W3204161688 creator A5004650249 @default.
- W3204161688 creator A5006617799 @default.
- W3204161688 creator A5007888987 @default.
- W3204161688 creator A5008334918 @default.
- W3204161688 creator A5008894717 @default.
- W3204161688 creator A5017587384 @default.
- W3204161688 creator A5031227461 @default.
- W3204161688 creator A5032356827 @default.
- W3204161688 creator A5043765267 @default.
- W3204161688 creator A5044181742 @default.
- W3204161688 creator A5045825594 @default.
- W3204161688 creator A5056830118 @default.
- W3204161688 creator A5067774356 @default.
- W3204161688 creator A5068480093 @default.
- W3204161688 date "2021-06-15" @default.
- W3204161688 modified "2023-09-26" @default.
- W3204161688 title "Scene Transformer: A unified architecture for predicting multiple agent trajectories" @default.
- W3204161688 cites W1504992226 @default.
- W3204161688 cites W1533861849 @default.
- W3204161688 cites W1836465849 @default.
- W3204161688 cites W2055207897 @default.
- W3204161688 cites W2148361676 @default.
- W3204161688 cites W2154844948 @default.
- W3204161688 cites W2183341477 @default.
- W3204161688 cites W2424778531 @default.
- W3204161688 cites W2532516272 @default.
- W3204161688 cites W2560609797 @default.
- W3204161688 cites W2606722458 @default.
- W3204161688 cites W2607296803 @default.
- W3204161688 cites W2626778328 @default.
- W3204161688 cites W2794787653 @default.
- W3204161688 cites W2937843571 @default.
- W3204161688 cites W2940129212 @default.
- W3204161688 cites W2949269657 @default.
- W3204161688 cites W2953212265 @default.
- W3204161688 cites W2953494151 @default.
- W3204161688 cites W2955189650 @default.
- W3204161688 cites W2963341956 @default.
- W3204161688 cites W2963858432 @default.
- W3204161688 cites W2964121744 @default.
- W3204161688 cites W2967177252 @default.
- W3204161688 cites W2968008415 @default.
- W3204161688 cites W2970116586 @default.
- W3204161688 cites W2970389371 @default.
- W3204161688 cites W2980087597 @default.
- W3204161688 cites W2981413347 @default.
- W3204161688 cites W2982745079 @default.
- W3204161688 cites W2983397630 @default.
- W3204161688 cites W2998108143 @default.
- W3204161688 cites W3012478636 @default.
- W3204161688 cites W3028769608 @default.
- W3204161688 cites W3032731803 @default.
- W3204161688 cites W3034722190 @default.
- W3204161688 cites W3035339264 @default.
- W3204161688 cites W3035574168 @default.
- W3204161688 cites W3048966129 @default.
- W3204161688 cites W3062588417 @default.
- W3204161688 cites W3073032883 @default.
- W3204161688 cites W3081405043 @default.
- W3204161688 cites W3090789587 @default.
- W3204161688 cites W3096609285 @default.
- W3204161688 cites W3097065222 @default.
- W3204161688 cites W3097237405 @default.
- W3204161688 cites W3098903812 @default.
- W3204161688 cites W3099312963 @default.
- W3204161688 cites W3106547440 @default.
- W3204161688 cites W3106944564 @default.
- W3204161688 cites W3107552218 @default.
- W3204161688 cites W3108486966 @default.
- W3204161688 cites W3119786062 @default.
- W3204161688 cites W3120885796 @default.
- W3204161688 cites W3124838366 @default.
- W3204161688 cites W3129901004 @default.
- W3204161688 cites W3132535424 @default.
- W3204161688 cites W3132577852 @default.
- W3204161688 cites W3133707750 @default.
- W3204161688 cites W3135588948 @default.
- W3204161688 cites W3139491754 @default.
- W3204161688 cites W3156216502 @default.
- W3204161688 cites W3160050461 @default.
- W3204161688 cites W3165444337 @default.
- W3204161688 cites W3169575318 @default.
- W3204161688 cites W3172509117 @default.
- W3204161688 cites W3179869055 @default.
- W3204161688 cites W3181350748 @default.
- W3204161688 cites W3204875639 @default.
- W3204161688 cites W3205301818 @default.
- W3204161688 cites W3208318476 @default.
- W3204161688 cites W2950268548 @default.
- W3204161688 hasPublicationYear "2021" @default.
- W3204161688 type Work @default.
- W3204161688 sameAs 3204161688 @default.
- W3204161688 citedByCount "3" @default.
- W3204161688 countsByYear W32041616882021 @default.
- W3204161688 countsByYear W32041616882022 @default.
- W3204161688 crossrefType "posted-content" @default.
- W3204161688 hasAuthorship W3204161688A5004650249 @default.
- W3204161688 hasAuthorship W3204161688A5006617799 @default.