提高运动预测中的上下文感知
Raising context awareness in motion forecasting
摘要：
基于学习的轨迹预测模型已经取得了巨大的成功，除了运动历史之外，还有望利用上下文信息。然而，我们发现，国家的最先进的预测方法往往过于依赖代理的当前动态，未能利用其输入提供的语义上下文线索。为了缓解这个问题，我们引入CAB，一个运动预测模型配备了一个训练过程，旨在促进使用语义上下文信息。我们还引入了两个新的指标-分散和收敛到范围-来衡量连续预测的时间一致性，我们发现在标准指标中缺少。我们的方法在广泛采用的nuScenes预测基准以及来自该基准的最困难示例的子集上进行评估。代码可在github.com/valeoai/CAB上获得
英文摘要：
Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history. Yet, we find that state-of-the-art forecasting methods tend to overly rely on the agent's current dynamics, failing to exploit the semantic contextual cues provided at its input. To alleviate this issue, we introduce CAB, a motion forecasting model equipped with a training procedure designed to promote the use of semantic contextual information. We also introduce two novel metrics - dispersion and convergence-to-range - to measure the temporal consistency of successive forecasts, which we found missing in standard metrics. Our method is evaluated on the widely adopted nuScenes Prediction benchmark as well as on a subset of the most difficult examples from this benchmark. The code is available at github.com/valeoai/CAB
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
