Publications

2026

Bridging Safety and Performance in Autonomous Systems using Offline Reinforcement Learning
NeurIPS'26
Bridging Safety and Performance in Autonomous Systems using Offline Reinforcement Learning
Mumuksh Tayal*, Manan Tayal*, R Prakash
* Equal contribution
40th Annual Conference on Neural Information Processing Systems (NeurIPS), Sydney, Australia
Preliminary version appeared at ICML 2026 Workshop: Agents in the Wild (AIWILD)
Paper Workshop Paper
DiffusionPack: Offline Bin Packing with Custom Human Preferences
RA-L'26
DiffusionPack: Offline Bin Packing with Custom Human Preferences
A Maurya, S Vats, G Balachandran, R Prakash
IEEE Robotics and Automation Letters
Preliminary version appeared at NeurIPS 2025 Workshop: Bridging Language, Agent, and World Models for Robotics
Paper Workshop Paper Project Site
V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
TMLR'26
V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
Mumuksh Tayal*, Manan Tayal*, A Singh, S Kolathaya, R Prakash
* Equal contribution
Transactions on Machine Learning Research
Preliminary version appeared at AAAI 2026 Workshop on Deployable AI (DAI) (Oral)
Paper Code Project Site
Sequentially Teaching Sequential Tasks (ST)2: Teaching Robots Long-Horizon Manipulation Skills
RA-M'26
Sequentially Teaching Sequential Tasks (ST)2: Teaching Robots Long-Horizon Manipulation Skills
Z Ajanović, R Prakash, L de Souza Rosa, J Kober
IEEE Robotics and Automation Magazine
Paper
Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution
IROS'26
Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution
H Zhang, K Nguyen, C Munasinghe, B Hela, T Li, Z Luo, H Nguyen, HW van de Venn, Y Zheng, R Prakash, TD Ta, A Nguyen, B Huang
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Pittsburgh, USA
Paper Project Site
Gripper-aware Vision Language Action Models
ECCV'26
Gripper-aware Vision Language Action Models
H Zhang, Z Luo, T Li, K Nguyen, B Hela, S Kumar, ND Tran, F Dai, C Munasinghe, J Peña Queralta, G Toffetti, K Vo, N Le, R Prakash, Q Vuong, TD Ta, L Hu, A Nguyen, B Huang
European Conference on Computer Vision (ECCV), Malmö, Sweden
Paper Project Site
Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
RLC'26
Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
Mumuksh Tayal*, Manan Tayal*, R Prakash
* Equal contribution
Reinforcement Learning Conference (RLC), Montréal, Canada
Preliminary version appeared at ICML 2026 Workshop: Agents in the Wild (AIWILD)
Paper Workshop Paper Project Site
AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers
CVPR'26
AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers
N Vu, T Do, K Nguyen, B Huang, N Le, BX Nguyen, E Tjiputra, QD Tran, R Prakash, T-C Chiu, A Nguyen
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Denver, USA
Paper Code Project Site
SafeDMPs: Integrating Formal Safety with DMPs for Adaptive HRI
ICRA'26
SafeDMPs: Integrating Formal Safety with DMPs for Adaptive HRI
P Tiwari, S Nath, R Prakash
IEEE International Conference on Robotics and Automation (ICRA), Vienna, Austria
Preliminary version appeared at CoRL 2025 2nd Workshop: Safe and Robust Robot Learning for Operation in the Real World
Paper Project Site Workshop Paper
Beyond the Teacher: Leveraging Mixed-Skill Demonstrations for Robust Imitation Learning
ICRA'26
Beyond the Teacher: Leveraging Mixed-Skill Demonstrations for Robust Imitation Learning
S Saharsh*, S Sonkar*, P Jagtap, R Prakash
* Equal contribution
IEEE International Conference on Robotics and Automation (ICRA), Vienna, Austria
Preliminary version appeared at CoRL 2025 Workshop: Making Sense of Data in Robotics: Composition, Quality, and Data-centric Approaches
Paper Code Project Site Workshop Paper
Safe and Optimal Variable Impedance Control via Certified Reinforcement Learning
ICRA'26
Safe and Optimal Variable Impedance Control via Certified Reinforcement Learning
S Kumar, R Prakash
IEEE International Conference on Robotics and Automation (ICRA), Vienna, Austria
Paper Code
Preview coming soon
CoRLW'26
Corrections Are Evidence, Not Targets: Operator-Aware Inversion for Adapting Frozen Generative Robot Policies
R Jadhav, S Bobade, S Viswanathan, SK Vidyarthi, L Nageswar, R Prakash
CoRL 2026 Workshop on Learning from Corrections and Interventions (LfC), Austin, USA
Paper
Preview coming soon
RSSW'26
Where Reasoning Does Not Matter: Isolating Chain-of-Thought in a Modular, Agentic VLM Manipulation Pipeline
B Hela, R Prakash
RSS 2026 Workshop: Semantic Reasoning and Goal Understanding in Robotics (SemRob), Sydney, Australia
Paper
Preview coming soon
ICRAW'26
Latent Dynamics Modulation Guidance for Semantic Obstacle Avoidance in Diffusion Policies
S Alavala, V Buereddy, R Prakash
ICRA 2026 Workshop: Semantics for Reliable Robot Autonomy, Vienna, Austria
Paper
Preview coming soon
ICRAW'26
The Topological Cage: A Search-Less Geometric Handshake for Medial Axis Injection
SP Goswami, R Prakash
ICRA 2026 Workshop: Geometry in the Age of Data-Driven Robotics, Vienna, Austria
Paper
Preview coming soon
CVPRW'26
GenieMotion: Learning Object-Centric 4D Motion Representations from a Single Image via Generative Demonstrations
M Halder, R Prakash
CVPR 2026 Workshop: 4D Vision, Denver, USA
Paper
Preview coming soon
ICRAW'26
State-Corrected Predictive Preference Learning for Multimodal Robot Navigation on Uneven Terrain
R Jadhav, AK Singh, S Ganguly, R Prakash, V Kumar
ICRA 2026 Workshop: Long-term Deployments in the Wild (LoWi), Vienna, Austria
Paper

2025

OVITA: Open-Vocabulary Interpretable Trajectory Adaptations
RA-L'25
OVITA: Open-Vocabulary Interpretable Trajectory Adaptations
A Maurya, T Ghosh, A Nguyen, R Prakash
IEEE Robotics and Automation Letters
Preliminary version appeared at CoRL 2024 Workshop on Language and Robot Learning (LangRob)
Paper Code
Generalizable motion policies through keypoint parameterization and transportation maps
T-RO'25
Generalizable motion policies through keypoint parameterization and transportation maps
G Franzese, R Prakash, C Della Santina, J Kober
IEEE Transactions on Robotics
Paper Code
Impedance Primitive-Augmented Hierarchical Reinforcement Learning for Sequential Tasks
ICRA'25
Impedance Primitive-Augmented Hierarchical Reinforcement Learning for Sequential Tasks
AB Tahmaz, R Prakash, J Kober
IEEE International Conference on Robotics and Automation (ICRA), Atlanta, USA
Paper
RISE: Robust Imitation through Stochastic Encodings
IROSW'25
RISE: Robust Imitation through Stochastic Encodings
Mumuksh Tayal, Manan Tayal, R Prakash
IROS 2025 Workshop: LeaPRIDE: Learning, Planning, and Reasoning in Dynamic Environments, Hangzhou, China
Paper
PACER: Progress-Aligned Curation for Error-Resilient Imitation Learning
CoRLW'25
PACER: Progress-Aligned Curation for Error-Resilient Imitation Learning
S Kumar, R Prakash
CoRL 2025 Workshop: Making Sense of Data in Robotics: Composition, Quality, and Data-centric Approaches, Seoul, South Korea
Paper

2024

Adaptive Critic Optimal Control of an Uncertain Robot Manipulator With Applications
T-CST'24
Adaptive Critic Optimal Control of an Uncertain Robot Manipulator With Applications
R Prakash, L Behera, S Jagannathan
IEEE Transactions on Control Systems Technology
Paper
3rd Workshop on Human-Interactive Robot Learning (HIRL)
HRI'24
3rd Workshop on Human-Interactive Robot Learning (HIRL)
M Racca, R Mirsky, E Senft, X Xiao, I Idrees, A Kshirsagar, R Prakash
ACM/IEEE International Conference on Human-Robot Interaction (HRI), Boulder, USA
Paper