Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.
Correcting robot plans with natural language feedback
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
RT-H learns robot policies by first predicting language motions as an intermediate representation and then mapping those plus the high-level task to actions, yielding more robust multi-task performance and the ability to learn from language interventions.
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
Freeform Preference Learning trains language-conditioned multi-axis reward models from human pairwise preferences to produce steerable and compositional robot policies that outperform sparse and binary-preference baselines by 38 percentage points.
E-MPC is a model predictive control framework that uses a user interaction dynamics model to balance autonomy and engagement under workload constraints in robotic caregiving, evaluated via simulation and a user study.
EgoPriMo learns a unified egocentric motion prior with a Triple-stream DiT model that supports reconstruction, generation, and forecasting of SMPL motions from egocentric views and text, outperforming prior methods and transferable to humanoid controllers.
A physical agentic loop with execution-state monitoring improves robustness of language-guided grasping over open-loop execution by converting noisy telemetry into discrete outcome events that trigger retries or user escalation.
PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.
Introduces EmbodiedUS-FS, a fast-slow hierarchical controller for robotic ultrasound that uses intent parsing, task graphs, multimodal feedback, and a safety shield to raise success rates and cut violations under motion and contact changes.
citing papers explorer
-
Code as Policies: Language Model Programs for Embodied Control
Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.
-
RT-H: Action Hierarchies Using Language
RT-H learns robot policies by first predicting language motions as an intermediate representation and then mapping those plus the high-level task to actions, yielding more robust multi-task performance and the ability to learn from language interventions.
-
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
-
Freeform Preference Learning for Robotic Manipulation
Freeform Preference Learning trains language-conditioned multi-axis reward models from human pairwise preferences to produce steerable and compositional robot policies that outperform sparse and binary-preference baselines by 38 percentage points.
-
Beyond Failure Recovery: An Engagement-Aware Human-in-the-loop Framework for Robotic Systems
E-MPC is a model predictive control framework that uses a user interaction dynamics model to balance autonomy and engagement under workload constraints in robotic caregiving, evaluated via simulation and a user study.
-
EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control
EgoPriMo learns a unified egocentric motion prior with a Triple-stream DiT model that supports reconstruction, generation, and forecasting of SMPL motions from egocentric views and text, outperforming prior methods and transferable to humanoid controllers.
-
A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring
A physical agentic loop with execution-state monitoring improves robustness of language-guided grasping over open-loop execution by converting noisy telemetry into discrete outcome events that trigger retries or user escalation.
-
Ignore Previous Prompt: Attack Techniques For Language Models
PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.
-
EmbodiedUS-FS: Fast Slow Intelligence for Ultrasound Robotics
Introduces EmbodiedUS-FS, a fast-slow hierarchical controller for robotic ultrasound that uses intent parsing, task graphs, multimodal feedback, and a safety shield to raise success rates and cut violations under motion and contact changes.