REVIEW 17 cited by
REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The ability to detect and analyze failed executions automatically is crucial for an explainable and robust robotic system. Recently, Large Language Models (LLMs) have demonstrated strong reasoning abilities on textual inputs. To leverage the power of LLMs for robot failure explanation, we introduce REFLECT, a framework which queries LLM for failure reasoning based on a hierarchical summary of robot past experiences generated from multisensory observations. The failure explanation can further guide a language-based planner to correct the failure and complete the task. To systematically evaluate the framework, we create the RoboFail dataset with a variety of tasks and failure scenarios. We demonstrate that the LLM-based framework is able to generate informative failure explanations that assist successful correction planning.
Forward citations
Cited by 17 Pith papers
-
Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference
Fail2Progress generates failure-targeted simulation data via Stein variational inference and fine-tunes skill effect models, improving long-horizon manipulation success rates and generalizing to unseen object counts a...
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.
-
CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation
Action-conditioned world-model verification with conformal first-intervention control and latency-aware suffix repair raises RoboCasa365 success 8.5 points over invocation-matched periodic replanning.
-
LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory
A chemical-lab failure sim, 20K-trajectory dataset, six-axis benchmark, and specialized VLM raise failure detection to 90.8% on seen scenes and lift downstream policy success by 4–16 points.
-
Try Once, Then Optimal: De-Redundified Procedure Memory for Cross-Episode Exploration Amortization
Object-centric procedure memory amortizes hidden-state exploration across encounters, cutting robot manipulation operations 16–30% at non-regressing success.
-
FORGE-plus: Force-Budgeted Recovery for Contact-Rich Assembly with a Frozen LLM Supervisor
With a hidden per-episode breaking force, an LLM-set force ceiling plus force-signature recovery achieves 256/256 clean insertions on fragile and robust parts and resolves 40–64% of injected jams in simulation.
-
PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution
A file-based operating-system layer with a session verifier and persistent memory improves embodied-agent task completion on game, simulated, and real-robot platforms without retraining policies.
-
From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
Outcome-based GRPO plus initial/current-state image anchors turns a 7B video MLLM into a progress critic that halves MAE versus specialized baselines and reaches 67% on RoboFail zero-shot.
-
LLM-Driven Self-Refinement for Embodied Drone Task Planning
SRDrone combines continuous state evaluation with hierarchical Behavior Tree repair so that LLM-based drone planners can autonomously refine their own plans after failures.
-
CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model
By iteratively retraining on automatically generated corrective examples derived from its own wrong paths, CorrectNav reports new state-of-the-art success rates of 65.1% (R2R-CE) and 69.3% (RxR-CE).
-
GhostShell: Streaming LLM Function Calls for Concurrent Embodied Programming
A streaming XML function-token interface with multi-channel scheduling lets robots execute concurrent speech and motion while the LLM is still generating, reportedly beating native function calling 15/15 vs 6/15 on co...
-
Conditional Multi-Stage Failure Recovery for Embodied Agents
A conditional four-stage chain-prompting method for failure recovery improves success on the TEACH embodied-agent benchmark from 24.9% to 36.5% with the same plan and executor.
-
Unsupervised Discovery of Failure Taxonomies from Deployment Logs
An unsupervised pipeline converts robot failure videos into natural language explanations, clusters them into recurring failure types, and uses those types to guide data collection and runtime monitoring.
-
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Embodied-R1.5 is an 8B EFM achieving SOTA on 16 of 24 embodied VLM benchmarks, fine-tunable to outperform leading VLAs, with claimed zero-shot real-robot generalization.
-
Personalised Explanations in Long-term Human-Robot Interactions
A two-stage LLM pipeline that first generates an explanation and then personalises it using a stored user knowledge memory reduces explanation length only when the user has related prior knowledge, in synthetic hospit...
-
Data Pyramid for Embodied Manipulation
Embodied training data form a five-layer pyramid—real-robot, UMI, ego/exo, simulation, general V–L—ordered by the trade-off between scale and robot alignment, and model capabilities track how those layers are mixed.
-
Human-Centered Shared Autonomy for Motor Planning, Learning, and Control Applications
A review chapter that organizes BCI, rehabilitation, and assistive robotics under a single adaptive-arbitration framework and illustrates it with the authors' own prior systems.
Discussion (0). Continue with ORCID to comment.