Merge branch 'pages' of https://github.com/Thinklab-SJTU/Bench2Drive …

…into pages

index.html

@@ -643,20 +643,20 @@ <h1>Bench2Drive</h1>
 											class="et_pb_module et_pb_text et_pb_text_1 et_pb_text_align_justified et_pb_bg_layout_dark">
 											<div class="et_pb_text_inner">
 												<p>
-												Bench2Drive is the first benchmark designed to rigorously evaluate E2E-AD systems under a closed-loop manner. 
+												Bench2Drive is the first benchmark for evaluating E2E-AD systems’ multiple abilities in a closed-loop manner. 
 												Bench2Drive consists of 2 million fully annotated frames as official training data, collected from 10000 short 
-												clips uniformly distributed under 43 interactive scenarios (cut-in, overtaking, detour, etc), 
-												27 weathers (sunny, foggy, rainy, etc), and 12 towns (urban, village, university, etc) in CARLA v2. 
-												Its evaluation protocol requires E2E-AD models to pass those 43 interactive scenarios under different 
-												locations which sums up to 215 routes and thus provide a comprehensive and disentangled assessment 
+												clips uniformly distributed under 44 interactive scenarios (cut-in, overtaking, detour, etc), 
+												23 weathers (sunny, foggy, rainy, etc), and 12 towns (urban, village, university, etc) in CARLA v2. 
+												Its evaluation protocol requires E2E-AD models to pass those 44 interactive scenarios under different 
+												locations which sums up to 220 routes and thus provide a comprehensive and disentangled assessment 
 												about their driving capability under different situations. We implement state-of-the-art E2E-AD models 
 												and evaluate them in Bench2Drive to provide more insights regarding current status of E2E-AD.
 												</p>
 												<p style="text-align: left">Key Features:</p>
 												<div>
 													<ul>
 														<li style="text-align: left">
-															Comprehensive scenario coverage: 100k clips, 43 scenarios, 27 weathers, 12 towns.
+															Comprehensive scenario coverage: 100k clips, 44 scenarios, 23 weathers, 12 towns.
 														</li>
 														<li style="text-align: left">
 															Expert information: intermediate features, reinforcement learning reward, value and action.
@@ -997,7 +997,13 @@ <h2 class="title is-3">BibTeX
 @article{jia2024bench,
   title={Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving},
   author={Xiaosong Jia and Zhenjie Yang and Qifeng Li and Zhiyuan Zhang and Junchi Yan},
-  journal={\url{https://github.com/Thinklab-SJTU/Bench2Drive}},
+  journal={arXiv preprint arXiv:2406.03877},
+  year={2024}
+}
+@article{li2024think,
+  title={Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)},
+  author={Qifeng Li and Xiaosong Jia and Shaobo Wang and Junchi Yan},
+  journal={arXiv preprint arXiv:2402.167200},
   year={2024}
 }</code></pre>
 										</div>