Unverified50% confidenceFactExact time
In a closed-loop trajectory, a single action deviation puts the robot into a state outside the training distribution, and each subsequent step compounds error on top of the mistake, ultimately causing the entire episode to collapse—a failure that may show up as only a few percentage points of decline in average success rate.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBehavior Cloning (BC) suffers from the covariate shift problem: during training the model only sees the state distribution of expert trajectories, and at deployment small errors can drive the robot into states not covered by the training set, leading to cascading failures.78% similarVerified仅用成功轨迹训练的模型往往存在分布外泛化的严重缺陷，遇到工具返回错误时便丧失纠偏能力78% similarVerifiedBehavioral cloning suffers from the distribution shift problem, where the model tends to make errors and accumulate mistakes on states outside the training distribution, a phenomenon referred to as compounding error in the robotics control field.77% similarUnverifiedErrors in robot trajectory data propagate along the temporal dimension, and a single early erroneous action can cause the entire subsequent trajectory to deviate from the normal distribution.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058613API
curl https://kongchang.com/api/v1/knowledge/claims/1058613MCP
get_claim(id=1058613)