long-horizon-manipulation

Tag

Cards List
#long-horizon-manipulation

From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation

Hugging Face Daily Papers ↗ · 2026-10-21 Cached

论文提出 SERA(Self-Evolving Robotic Agent),通过可编辑的 harness 维护任务上下文并利用执行反馈自我进化规划,配合固定的 VLA 执行器来改进长时程机器人操作任务,在 RoboMME 上取得 51.38% 的成功率。

0 favorites 0 likes
#long-horizon-manipulation

RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation

Hugging Face Daily Papers ↗ · 2026-10-20 Cached

RoboCasa-Shift 提出一个基于 RoboCasa365 的阶段感知鲁棒性基准,通过配对 rollout 与受控扰动评估视觉-语言-动作(VLA)策略在长程家务操作任务中的表现,发现失败模式随扰动因子和任务而异,并非均匀退化,主张鲁棒性应作为执行的多维属性而非单一端到端指标衡量。

0 favorites 0 likes
#long-horizon-manipulation

Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation

Hugging Face Daily Papers ↗ · 2026-10-13 Cached

提出了Orchestra,一种将任务规划与执行管理同动作生成分离的机器人智能体框架,用于执行多步多模态指令的长时程操作,并发布了基准RMBench-Compose。Orchestra在多个基准和真实世界多步任务上显著超越Mem-0和HarnessVLA等基线。

0 favorites 0 likes
#long-horizon-manipulation

SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

Hugging Face Daily Papers ↗ · 2026-09-02 Cached

SimpleMemVLA introduces a simple memory mechanism for Vision-Language-Action models by feeding intact timestamped video history into a pretrained VLM backbone, achieving state-of-the-art results on long-horizon manipulation tasks without dedicated memory modules.

0 favorites 0 likes
#long-horizon-manipulation

EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

Hugging Face Daily Papers ↗ · 2026-06-18 Cached

EventVLA introduces a sparse visual evidence memory framework for long-horizon robotic manipulation, achieving an average success rate improvement of +40% over state-of-the-art memory-augmented VLAs.

0 favorites 0 likes
← Back to home

Submit Feedback