M.Sc. Thesis Robotics & AI NUST, Pakistan

Safe Dual-Arm Cable Routing
with Deformable Linear Objects

Hierarchical Planning & Contact-Aware Control Barrier Functions

Muhammad Mahad · Supervised by Dr. Karam Dad Kallu

Scroll to explore

Demo

Two Franka Emika Panda arms performing autonomous pick-up, contact-aware handover, and smooth millimeter-scale placement in MuJoCo.

Pick-up

Right arm approaches with top-down orientation and establishes firm grasp

Handover

Contact-aware transfer with 10 mm distance sensing & synchronized clamping

Place

Minimum-jerk interpolated carry to target with inertial-slip prevention

Overview

This thesis proposes a hierarchical collision-avoidance framework for dual-arm cable routing in simulation, handling three distinct safety aspects simultaneously.

01

Arm–Arm Self-Collision

Prevent the two 7-DoF manipulators from colliding with each other during coordinated motion.

02

Arm/Cable Environment

Ensure neither robot arms nor the cable contact environmental obstacles (walls, fixtures, workspace boundaries).

03

Contact-Aware Fixtures

Distinguish desired clip insertions from unintended collisions, enabling safe cable routing through fixtures.

14-DoF + DLO State Space
CBF Safety Filter
Safe
Motion

Hierarchical Architecture

A two-level planning and control pipeline: a global planner computes coarse collision-free paths, tracked by a local MPC controller wrapped in a safety-certified CBF.

Level 1

Global Motion Planner

DIT* or JIT in 14-DoF + DLO configuration space

Catenary-aware cost DLO collision checking Asymptotically optimal
Coarse path
Level 2

Local Controller

MPC + Mode-Switching CBF-QP Safety Filter

harm-arm ≥ 0 harm-env ≥ 0 hcable-env ≥ 0 Tension limits
Safe commands
Simulation

MuJoCo + Adapted DER

Dual Franka Panda + Discrete Elastic Rods cable model

CPU-efficient Python / C++ API No ROS middleware
🔄

Contact-Aware Mode Switching

The CBF dynamically switches modes when force-torque sensors detect a Contact Establishment Indicator (CEI) near routing clips to temporarily relaxing hcable-env to allow fixture insertion while maintaining all other safety guarantees.

Tech Stack

🔬

MuJoCo 3.x

Physics simulation via direct Python/C++ API without middleware overhead

🤖

Dual Franka Panda

Two 7-DoF manipulators from vikashplus/frankasim

🧮

mink IK

Pinocchio-based differential inverse kinematics for real-time control

🧬

Adapted DER

Discrete Elastic Rods for realistic cable bending, twisting & sagging

🛡️

CBF-QP

Control Barrier Functions via OSQP / qpOASES for certified safety

🗺️

DIT* or JIT

State-of-the-art asymptotically optimal global motion planners

🔌

ROS Integration

Seamless hardware synchronization for future real-world deployment

6-Month Timeline

Month 1
✅ Completed

Simulation Setup & Minimal Interface

MuJoCo dual-arm environment constructed via direct API. Rigid-body baseline with 19-phase pick-handover-place demo operational.

Month 2
🔲 Planned

Local Control & Baseline Safety

MPC tracking controller and core CBF constraints (arm-arm, environment, tension) using geometric distance queries.

Month 3
🔲 Planned

Global Planner Integration

DIT* or JIT adapted for DLOs with catenary-aware cost function and DLO-inclusive collision checking.

Month 4
🔲 Planned

Contact-Aware Mode Switching

Force-simulated CEI implementation and mode-switching CBF logic for clip insertions.

Month 5
🔲 Planned

Dynamic Stress Testing

Evaluation: fast motions, dynamic obstacle avoidance. Benchmarking against standard MPC and vanilla RRT.

Month 6
🔲 Planned

Thesis Writing & Defense

Data analysis, final manuscript drafting, and defense presentation formatting.

Key References

  1. Yin, H., Varava, A., & Kragic, D. (2021). "Modeling, learning, perception, and control methods for deformable object manipulation." Science Robotics, 6(54).
  2. Yu, M., et al. (2023). "A coarse-to-fine framework for dual-arm manipulation of deformable linear objects with whole-body obstacle avoidance." ICRA 2023.
  3. Chen, K., Bing, Z., et al. (2023). "Contact-aware Shaping and Maintenance of Deformable Linear Objects With Fixtures." IROS 2023.
  4. Chen, K., et al. (2024). "Real-time Contact State Estimation in Shape Control of DLOs under Small Environmental Constraints." ICRA 2024.
  5. Zhang, L., et al. (2025). "Direction Informed Trees (DIT *): Optimal Path Planning via Direction Filter and Direction Cost Heuristic." arXiv:2508.19168.
  6. Cai, K., Zhang, L., et al. (2026). "Just in time Informed Trees: Manipulability-Aware Asymptotically Optimized Motion Planning." arXiv:2601.19972.
  7. Zhu, J., et al. (2019). "Robotic manipulation planning for shaping deformable linear objects with environmental contacts." IEEE RA-L.
  8. Zeng, Q., et al. (2023). "Accurate Simulation and Parameter Identification of DLOs in MuJoCo." arXiv:2310.00911.