SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.07601 · ECCV · 2022

ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning

Dacheng Tao, Junchi Yan, Hongyang Li, Li, Penghao Wu, Shengchao Hu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
opendrivelab/st-p3 pwc_unofficial 5 of 5
FunctionStatusWhere it lives
conv_1x1x1_norm_activated Ran opendrivelab/st-p3/stp3/layers/temporal.py
code served (permissive licence) · get_code("0aa4fbf8c08322f6")
get_warp_transform Ran opendrivelab/st-p3/maps/hdmap_generate.py
code served (permissive licence) · get_code("97869cb697d57b62")
make_contour Ran opendrivelab/st-p3/carla_agent.py
code served (permissive licence) · get_code("b6c5b51ee23dcae9")
tint Ran opendrivelab/st-p3/maps/hdmap_generate.py
code served (permissive licence) · get_code("666bff0c1b718eb4")
world_to_pixel Ran opendrivelab/st-p3/maps/hdmap_generate.py
code served (permissive licence) · get_code("0527e29d9fa34691")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Many existing autonomous driving paradigms involve a multistage discrete pipeline of tasks. To better predict the control signals and enhance user safety, an end-to-end approach that benefits from joint spatial-temporal feature learning is desirable. While there are some pioneering works on LiDAR-based input or implicit design, in this paper we formulate the problem in an interpretable vision-based setting. In particular, we propose a spatial-temporal feature learning scheme towards a set of more representative features for perception, prediction and planning tasks simultaneously, which is called ST-P3. Specifically, an egocentric-aligned accumulation technique is proposed to preserve geometry information in 3D space before the bird's eye view transformation for perception; a dual pathway modeling is devised to take past motion variations into account for future prediction; a temporal-based refinement unit is introduced to compensate for recognizing vision-based elements for planning. To the best of our knowledge, we are the first to systematically investigate each part of an interpretable end-to-end vision-based autonomous driving system. We benchmark our approach against previous state-of-the-arts on both open-loop nuScenes dataset as well as closed-loop CARLA simulation. The results show the effectiveness of our method. Source code, model and protocol details are made publicly available at https://github.com/OpenPerceptionX/ST-P3.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.07601")
get_code_for_paper("2207.07601")
have("2207.07601")

Connect an agent — have() is free.