Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network

• URL: http://arxiv.org/abs/2207.00738v1
• Date: Sat, 2 Jul 2022 04:57:44 GMT
• Title: Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network
• Authors: Xiaocheng Tang, Soheil Sadeghi Eshkevari, Haoyu Chen, Weidan Wu, Wei Qian, Xiaoming Wang
• Abstract summary: We propose a general Transformer-like architectural module MnM network equipped with novel masked goal conditioning training procedures for AV trajectory prediction. The model, named golfer, achieves state-of-the-art performance, winning the 2nd place in the 2022 Open Motion Prediction Challenge and ranked 1st place according to minADE.
• Score: 16.393675040056397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformers have enabled breakthroughs in NLP and computer vision, and have recently began to show promising performance in trajectory prediction for Autonomous Vehicle (AV). How to efficiently model the interactive relationships between the ego agent and other road and dynamic objects remains challenging for the standard attention module. In this work we propose a general Transformer-like architectural module MnM network equipped with novel masked goal conditioning training procedures for AV trajectory prediction. The resulted model, named golfer, achieves state-of-the-art performance, winning the 2nd place in the 2022 Waymo Open Dataset Motion Prediction Challenge and ranked 1st place according to minADE.

Related papers

• Vectorized Representation Dreamer (VRD): Dreaming-Assisted Multi-Agent Motion-Forecasting [2.2020053359163305]
  We introduce VRD, a vectorized world model-inspired approach to the multi-agent motion forecasting problem. Our method combines a traditional open-loop training regime with a novel dreamed closed-loop training pipeline. Our model achieves state-of-the-art performance on the single prediction miss rate metric.
  arXiv  Detail & Related papers  (2024-06-20T15:34:17Z)
• Valeo4Cast: A Modular Approach to End-to-End Forecasting [93.86257326005726]
  Our solution ranks first in the Argoverse 2 End-to-end Forecasting Challenge, with 63.82 mAPf. We depart from the current trend of tackling this task via end-to-end training from perception to forecasting, and instead use a modular approach. We surpass forecasting results by +17.1 points over last year's winner and by +13.3 points over this year's runner-up.
  arXiv  Detail & Related papers  (2024-06-12T11:50:51Z)
• STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition [50.064502884594376]
  We study the problem of human action recognition using motion capture (MoCap) sequences. We propose a novel Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh sequences. The proposed method achieves state-of-the-art performance compared to skeleton-based and point-cloud-based models.
  arXiv  Detail & Related papers  (2023-03-31T16:19:27Z)
• Single Stage Multi-Pose Virtual Try-On [119.95115739956661]
  Multi-pose virtual try-on (MPVTON) aims to fit a target garment onto a person at a target pose. MPVTON provides a better try-on experience, but is also more challenging due to the dual garment and pose editing objectives. Existing methods adopt a pipeline comprising three disjoint modules including a target semantic layout prediction module, a coarse try-on image generator and a refinement try-on image generator. In this paper, we propose a novel single stage model forTON. Key to our model is a parallel flow estimation module that predicts the flow fields for both person and garment images conditioned on
  arXiv  Detail & Related papers  (2022-11-19T15:02:11Z)
• Motion Transformer with Global Intention Localization and Local Movement Refinement [103.75625476231401]
  Motion TRansformer (MTR) models motion prediction as the joint optimization of global intention localization and local movement refinement. MTR achieves state-of-the-art performance on both the marginal and joint motion prediction challenges.
  arXiv  Detail & Related papers  (2022-09-27T16:23:14Z)
• MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction [103.75625476231401]
  We propose a novel Motion Transformer framework for multimodal motion prediction, which introduces a small set of novel motion query pairs. A simple model ensemble strategy with non-maximum-suppression is adopted to further boost the final performance. Our approach achieves the 1st place on the motion prediction leaderboard of 2022 Open dataset Challenges, outperforming other methods with remarkable margins.
  arXiv  Detail & Related papers  (2022-09-20T23:03:22Z)
• MotionCNN: A Strong Baseline for Motion Prediction in Autonomous Driving [6.10183951877597]
  We present a simple and yet very strong baseline for multimodal motion prediction based purely on Convolutional Neural Networks. Our source code is publicly available at GitHub.
  arXiv  Detail & Related papers  (2022-06-05T12:31:58Z)
• Transformer based trajectory prediction [71.31516599226606]
  We present a simple and yet strong baseline for uncertainty aware motion prediction based purely on transformer neural networks. While being easy-to-implement, the proposed approach achieves competitive performance and ranks 1$st$ on the 2021 Shifts Vehicle Motion Prediction Competition.
  arXiv  Detail & Related papers  (2021-12-08T16:00:14Z)
• DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets [29.239524389784606]
  We propose an anchor-free and end-to-end trajectory prediction model, named DenseTNT, that directly outputs a set of trajectories from dense goal candidates. DenseTNT achieves state-of-the-art performance, ranking 1st on the Argoverse motion forecasting benchmark and being the 1st place winner of the 2021 Open Motion Prediction Challenge.
  arXiv  Detail & Related papers  (2021-08-22T05:27:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.