MISTY delivers state-of-the-art closed-loop scores on nuPlan Test14-hard (80.32 non-reactive, 82.21 reactive) at 10.1 ms latency via single-step MLP-Mixer inference and a latent drifting loss that encourages proactive maneuvers.
hub
Pluto: Pushing the limit of imitation learning- based planning for autonomous driving.ArXiv, abs/2404.14327
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
abstract
We present PLUTO, a powerful framework that pushes the limit of imitation learning-based planning for autonomous driving. Our improvements stem from three pivotal aspects: a longitudinal-lateral aware model architecture that enables flexible and diverse driving behaviors; An innovative auxiliary loss computation method that is broadly applicable and efficient for batch-wise calculation; A novel training framework that leverages contrastive learning, augmented by a suite of new data augmentations to regulate driving behaviors and facilitate the understanding of underlying interactions. We assessed our framework using the large-scale real-world nuPlan dataset and its associated standardized planning benchmark. Impressively, PLUTO achieves state-of-the-art closed-loop performance, beating other competing learning-based methods and surpassing the current top-performed rule-based planner for the first time. Results and code are available at https://jchengai.github.io/pluto.
hub tools
years
2026 15representative citing papers
A dual-track zero-shot benchmark (DeepPlan semantic shift + actuation-noise drift) reveals imitation planners collapse under novel urban density and correlated noise while an RL planner remains more robust.
A diffusion-based autonomous driving planner that injects gradients from a spatio-temporal occupancy-and-route cost volume into late denoising steps improves closed-loop safety and progress across three benchmarks.
UniTeD unifies perception and planning in autonomous driving via shared temporal diffusion with TTM and ARS modules, reporting SOTA results on benchmarks.
Dash2Sim recovers metric geo-referenced 4D scenes from in-the-wild monocular dashcam videos to enable the ROADWork4D benchmark, revealing that current closed-loop planners fail on work zone lane changes.
Arbitration graphs that decouple verification and scoring from trajectory generation let Mosaic fuse PDM-Closed and FlowDrive* into a new SOTA closed-loop planner on nuPlan.
Conditioning speed planning on the predicted path and relabeling synthetic cut-ins yields SOTA Bench2Drive scores (DS 89.07, SR 73.18%).
R²LPL converts recoverable policy mistakes identified in closed-loop rollouts into corrective supervised targets for lifelong policy improvement, reaching SOTA on nuPlan benchmarks with few cycles.
ASSCG is an RWKV-based adaptive gate trained with SFT and GRPO-style RL that makes Query/Cache/Drop decisions for slow LLM guidance in fast-slow autonomous driving planners, improving scores and cutting latency on nuPlan and NAVSIM.
Diffusion Forcing Planner applies heterogeneous joint diffusion with time-dependent noise and classifier-free guidance on history segments to generate stable, controllable motion plans for autonomous driving on nuPlan.
Lightweight confidence-aware LM distilled from multi-agent CoT demonstrations achieves SOTA success rates on nuPlan benchmark for AD decision-making with low inference latency.
LVDrive improves closed-loop driving on Bench2Drive by adding latent future scene prediction to VLA models via unified embedding space processing and two-stage trajectory decoding.
SafeAlign-VLA uses counterfactual safety pairing and anchor-based group relative policy optimization to incorporate negative data for safer VLA-based autonomous driving.
LUNA-AD introduces a tri-system model with multi-agent hypothesis exploration, distilled lightweight inference, and reflection-driven lifelong learning that claims state-of-the-art success rates on nuPlan benchmarks with reduced latency.
citing papers explorer
-
MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting
MISTY delivers state-of-the-art closed-loop scores on nuPlan Test14-hard (80.32 non-reactive, 82.21 reactive) at 10.1 ms latency via single-step MLP-Mixer inference and a latent drifting loss that encourages proactive maneuvers.
-
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
A dual-track zero-shot benchmark (DeepPlan semantic shift + actuation-noise drift) reveals imitation planners collapse under novel urban density and correlated noise while an RL planner remains more robust.
-
G2DP: Diffusion Planning with Spatio-Temporal Grid Guidance
A diffusion-based autonomous driving planner that injects gradients from a spatio-temporal occupancy-and-route cost volume into late denoising steps improves closed-loop safety and progress across three benchmarks.
-
UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving
UniTeD unifies perception and planning in autonomous driving via shared temporal diffusion with TTM and ARS modules, reporting SOTA results on benchmarks.
-
Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos
Dash2Sim recovers metric geo-referenced 4D scenes from in-the-wild monocular dashcam videos to enable the ROADWork4D benchmark, revealing that current closed-loop planners fail on work zone lane changes.
-
Mosaic: An Extensible Framework for Composing Rule-Based and Learned Motion Planners
Arbitration graphs that decouple verification and scoring from trajectory generation let Mosaic fuse PDM-Closed and FlowDrive* into a new SOTA closed-loop planner on nuPlan.
-
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
Conditioning speed planning on the predicted path and relabeling synthetic cut-ins yields SOTA Bench2Drive scores (DS 89.07, SR 73.18%).
-
Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving
R²LPL converts recoverable policy mistakes identified in closed-loop rollouts into corrective supervised targets for lifelong policy improvement, reaching SOTA on nuPlan benchmarks with few cycles.
-
ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving
ASSCG is an RWKV-based adaptive gate trained with SFT and GRPO-style RL that makes Query/Cache/Drop decisions for slow LLM guidance in fast-slow autonomous driving planners, improving scores and cutting latency on nuPlan and NAVSIM.
-
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
Diffusion Forcing Planner applies heterogeneous joint diffusion with time-dependent noise and classifier-free guidance on history segments to generate stable, controllable motion plans for autonomous driving on nuPlan.
-
Decision-Making with Lightweight Confidence-Aware Language Model for Autonomous Driving
Lightweight confidence-aware LM distilled from multi-agent CoT demonstrations achieves SOTA success rates on nuPlan benchmark for AD decision-making with low inference latency.
-
LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
LVDrive improves closed-loop driving on Bench2Drive by adding latent future scene prediction to VLA models via unified embedding space processing and two-stage trajectory decoding.
-
SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving
SafeAlign-VLA uses counterfactual safety pairing and anchor-based group relative policy optimization to incorporate negative data for safer VLA-based autonomous driving.
-
LUNA-AD: Lightweight Uncertainty-Aware Language Model with Lifelong Learning for Autonomous Driving
LUNA-AD introduces a tri-system model with multi-agent hypothesis exploration, distilled lightweight inference, and reflection-driven lifelong learning that claims state-of-the-art success rates on nuPlan benchmarks with reduced latency.
- CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners