Research Output

Peer Reviewed Conference and Journal Publications (where * denotes equal contribution):

1. [RA-L 2025] W. Zhi, H. Tang, T. Zhang, M. Johnson-Roberson. Teaching Periodic Stable Robot Motion Generation Via Sketch. 

2. [RA-L 2025] T. Zhang, W. Zhi, et al. RecGS: Removing Water Caustic with Recurrent Gaussian Splatting. 

3. [T-RO 2025, accepted to appear] Multi-query Robotic Manipulator Task Sequencing with Gromov-Hausdorff Approximations. F. Sukkar, J. Wakulicz, K. M. B. Lee, W. Zhi, R. Fitch.

4. [RA-L 2025, accepted to appear] ModCube: Modular, Self-Assembling Cubic Underwater Robot. J. Zheng, et al., W. Zhi, D. Fan.

5. [Expert Syst. Appl. 2025] H. Wang, W. Zhi, G. Batista, R. Chandra. Pedestrian trajectory prediction using goal-driven and dynamics-based deep learning framework. Expert Syst. Appl., 2025.

6. [RA-L 2024] W. Zhi, H. Tang, T. Zhang, M. Johnson-Roberson. Simultaneous Geometry and Pose Estimation of Grasped Objects via 3D Foundation Models. 

7. [RA-L 2024] W. Zhi, H. Tang,  T. Zhang, M. Johnson-Roberson. Unifying Representation and Calibration with 3D Foundation Models. 

8. [IROS 2024] Q. Sun*, W. Zhi*, T. Zhang, M. Johnson-Roberson. Diagrammatic Instructions to Specify Spatial Objectives and Constraints with Applications to Mobile Base Placement. 

9. [IROS 2024] H. Wright, W. Zhi, M. Johnson-Roberson, T. Hermans. V-PRISM: Probabilistic Mapping of Unknown Tabletop Scenes. 

10. [IROS 2024] T. Zhang, K. Huang, W. Zhi, M. Johnson-Roberson. DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark. 

11. [IROS 2024] T. Lai, W.Zhi, T. Hermans, F. Ramos. Learning for Kinodynamic Tree Expansion. 

12. [ICRA 2024] W. Zhi, T. Zhang, M. Johnson-Roberson. Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching. 

13. [ICRA 2024] H. Wang, W.Zhi, G. Batista, R. Chandra. Pedestrian Trajectory Prediction Using Dynamics-based Deep Learning. 

14. [ICRA 2023] W. Zhi, I. Akinola, K. Van Wyk, N. Ratliff, F. Ramos. Global and Reactive Motion Generation with Geometric Fabric Command Sequences.  

15. [ICML 2022] W. Zhi, T. Lai, L. Ott, E. V. Bonilla, F. Ramos. Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks. 

16. [L4DC 2022, Best Paper Award] W. Zhi, T. Lai, L. Ott, F. Ramos. Diffeomorphic Transforms for Generalised Imitation Learning. 

17. [CORL 2021] T. Lai, W. Zhi, T. Hermans, F. Ramos. Parallelised Diffeomorphic Sampling-based Motion Planning. 

18. [IROS 2021] W. Zhi, L. Ott, F. Ramos. Probabilistic Trajectory Prediction with Structural Constraints. 

19. [IROS 2021] W. Zhi *, T. Lai *, L. Ott, F. Ramos. Trajectory Generation in New Environments from Past Experiences. 

20. [ICRA 2021] W. Zhi, T. Lai, L. Ott, F. Ramos. Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements. 

21. [CORL 2019] W. Zhi, L. Ott, F. Ramos Kernel trajectory maps for multi-modal probabilistic motion prediction.

22. [RA-L + IROS 2019] W. Zhi, R. Senanyake, L. Ott, F. Ramos. Spatiotemporal learning of directional uncertainty in urban environments with kernel recurrent mixture density networks. 

23. [ICRA 2019] W. Zhi, R. Senanyake, L. Ott, F. Ramos. Continuous Occupancy Map Fusion with Fast Bayesian Hilbert Maps. 

I have also published work on machine learning for medical imaging, prior to my PhD, these include:

• [DICTA 2017] Using convolutional neural networks and transfer learning for bone age classification. J. Zhou, Z. Li, W. Zhi, B. Liang, D. Moses, L., Dawes.

• [ICONIP 2017] Using transfer learning with convolutional neural networks to diagnose breast cancer from histopathological images. W. Zhi, H.W.F Yeung, Z. Chen, S.M. Zandavi, Z. Lu, Y.Y. Chung.