← Search

Kumar Manas

2 accepted papers

2025

Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification

RSS 2025poster

Deep learning-based trajectory prediction models have demonstrated promising capabilities in capturing complex interactions. However, their generalization beyond the available training data, limited in both size and diversity, remains a significant challenge. To improve generalization, we propose SH…

Cited by 0PDFcodeScholar
2024

CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning

IROS 2024poster

Autonomous agents often face the challenge of interpreting uncertain natural language instructions for planning tasks. Representing these instructions as Linear Temporal Logic (LTL) enables planners to synthesize actionable plans. We introduce CoT-TL, a data-efficient in-context learning framework f…

Cited by 2SourcecodeScholar